input.bib

@article{allan-swirl12,
  title = {{Frontiers, Challenges, and Opportunities for Information Retrieval -- Report from SWIRL 2012, The Second Strategic Workshop on Information Retrieval in Lorne}},
  author = {Allan, James and Aslam, Jay and Azzopardi, Leif and Belkin, Nick and Borlund, Pia and Bruza, Peter and Callan, Jamie and Carman, Mark and Clarke, Charles LA and Craswell, Nick and others},
  journal = {{SIGIR Forum}},
  volume = {46},
  number = {1},
  pages = {2--32},
  year = {2012},
  publisher = {ACM},
  url = {http://sigir.org/files/forum/2012J/2012j_sigirforum_A_allanSWIRL2012Report.pdf}
}
@inproceedings{Alonso11-crowdconf,
  author = {Omar Alonso and Matthew Lease},
  title = {Crowdsourcing For Research and Engineering},
  booktitle = {{Tutorial at CrowdConf 2011}},
  month = {November},
  day = {1},
  year = {2011},
  address = {San Francisco, CA},
  confurl = {http://crowdconf.com/workshops.html},
  slides = {http://www.slideshare.net/mattlease/crowdconf2011-tutorial-crowdsourcing-for-research-and-engineering}
}
@inproceedings{Alonso11-sigir,
  author = {Omar Alonso and Matthew Lease},
  title = {Crowdsourcing for Information Retrieval: Principles, Methods, and Applications},
  booktitle = {{Tutorial at the 34th Annual ACM SIGIR Conference}},
  month = {July},
  day = {24},
  year = {2011},
  address = {Beijing, China},
  isbn = {978-1-4503-0757-4},
  pages = {1299},
  acmid = {2010170},
  publisher = {ACM},
  keywords = {crowdsourcing, human computation},
  url = {http://portal.acm.org/citation.cfm?id=2010170},
  confurl = {http://www.sigir2011.org/crowdsourcing-for-information-retrieval.htm},
  slides = {http://www.slideshare.net/mattlease/crowdsourcing-for-information-retrieval-principles-methods-and-applications}
}
@inproceedings{Alonso11-wsdm,
  author = {Omar Alonso and Matthew Lease},
  title = {Crowdsourcing 101: Putting the WSDM of Crowds to Work for You},
  booktitle = {Tutorial at the Fourth ACM International Conference on Web Search 
and Data Mining (WSDM)},
  month = {February},
  day = {9},
  year = {2011},
  isbn = {978-1-4503-0493-1},
  pages = {1--2},
  acmid = {1935831},
  publisher = {ACM},
  keywords = {crowdsourcing, human computation},
  address = {Hong Kong, China},
  url = {http://dl.acm.org/citation.cfm?id=1935831},
  slides = {http://ir.ischool.utexas.edu/wsdm2011_tutorial.pdf},
  confurl = {http://www.wsdm2011.org/wsdm2011/tutorials#t-am1},
  abstract = {
Crowdsourcing has emerged in recent years as an exciting new avenue for 
leveraging the tremendous potential and resources of today.s 
digitally-connected, diverse, distributed workforce. Generally speaking, 
crowdsourcing describes outsourcing of tasks to a large group of people instead 
of assigning such tasks to an in-house employee or contractor. Crowdsourcing 
platforms such as Amazon Mechanical Turk and CrowdFlower have gained particular 
attention as active online market places for reaching and tapping into this glut 
of a still largely under-utilized workforce. Crowdsourcing offers intriguing new 
opportunities for accomplishing different kinds of tasks or achieving broader 
participation than previously possible, as well as completing standard tasks 
more accurately in less time and at lower cost. Unlocking the potential of 
crowdsourcing in practice, however, requires a tri-partite understanding of 
principles, platforms, and best practices. This tutorial will introduce the 
opportunities and challenges of crowdsourcing while discussing the three issues 
above. This will provide attendees with a basic foundation to begin applying 
crowdsourcing in the context of their own particular tasks. }
}
@inproceedings{Bies06,
  author = {Ann Bies and Stephanie Strassel and Haejoong Lee and Kazuaki Maeda and Seth Kulick and Yang Liu and Mary Harper and Matthew Lease},
  title = {Linguistic Resources for Speech Parsing},
  booktitle = {Fifth International Conference on Language Resources and Evaluation (LREC'06)},
  year = 2006,
  address = {Genoa, Italy},
  url = {http://papers.ldc.upenn.edu/LREC2006/LinguisticResourcesForSpeechParsing.pdf}
}
@inproceedings{Broussard10,
  author = {Ramona Broussard and Yongyi Zhou and Matthew Lease},
  title = {Mobile Phone Search for Library Catalogs},
  booktitle = {Proceedings of the 73rd Annual Meeting of the American Society for Information Science and Technology (ASIS\&T)},
  year = 2010,
  url = {../papers/broussard-asist10.pdf},
  note = {Short paper.},
  video = {../papers/zhou-brossard-mut.avi},
  source = {http://www.ischool.utexas.edu/~ramona/documents/mobileUT.zip},
  slides = {http://www.ischool.utexas.edu/~ramona/documents/broussard-asist-web.ppt},
  abstract = {While some libraries have begun to offer customized
mobile applications for their online public access catalogs
(OPACs), little research has investigated the relative costs
and benefits associated with developing such applications.
To investigate this tradeoff, we have developed a prototype
Mobile search application for the University of Texas
library catalog (MUT). Our experience indicates that
mobile applications for catalog access can be built at
relatively low cost and effort, with MUT providing a proof of
concept for developing similar mobile applications at
other institutions. Overall, our findings suggest customized
mobile applications have potential to significantly better
serve patrons in return for a relatively small investment in
development and maintenance.}
}
@inproceedings{Broussard10-2,
  author = {Ramona Broussard and Yongyi Zhou and Matthew Lease},
  title = {University of Texas Mobile Library Search},
  booktitle = {Proceedings of the 73rd Annual Meeting of the American Society for Information Science and Technology (ASIS\&T)},
  year = 2010,
  note = {Poster},
  video = {../papers/zhou-brossard-mut.avi},
  url = {../papers/broussard-asist10-poster.pdf},
  abstract = {This demonstration will showcase a prototype Mobile application we built for accessing the library catalog at the University of Texas. 
The demonstration is intended to complement the short paper, Mobile Phone Search for Library Catalogs that will appear at ASIS&T 2010. In particular, 
we will provide attendees a hands-on experience seeing and using our interface, as well as an opportunity to discuss design alternatives and tradeoffs 
with us in person. We will show how MUT can provide library patrons with a faster and easier access via a customized mobile application.}
}
@inproceedings{Buckley10-notebook,
  author = {Chris Buckley and Matthew Lease and Mark D. Smucker},
  title = {{Overview of the TREC 2010 Relevance Feedback Track (Notebook)}},
  booktitle = {{The Nineteenth Text Retrieval Conference (TREC) Notebook}},
  institute = {{National Institute of Standards and Technology (NIST)}},
  year = {2010},
  url = {../papers/trec-notebook-2010.pdf}
}
@inproceedings{Cartright09,
  author = {Marc Cartright and Jangwon Seo and Matthew Lease},
  title = {{UMass Amherst and UT Austin at the TREC'09 Relevance Feedback Track}},
  booktitle = {Proceedings of the 18th Text Retrieval Conference (TREC'09)},
  institute = {National Institute of Standards and Technology},
  year = 2010,
  url = {http://trec.nist.gov/pubs/trec18/papers/umass-amhearst.RF.pdf},
  abstract = {We present a new supervised method for es-
timating term-based retrieval models and ap-
ply it to weight expansion terms from relevance
feedback. While previous work on supervised
feedback [Cao et al., 2008] demonstrated signi-
cantly improved retrieval accuracy over standard
unsupervised approaches [Lavrenko and Croft,
erty, 2001], feedback terms
were assumed to be independent in order to
reduce training time. In contrast, we adapt
the AdaRank learning algorithm [Xu and Li,
2007] to simultaneously estimate parameteriza-
tion of all feedback terms. While not evaluated
here, the method can be more generally applied
for joint estimation of both query and feedback
terms. To apply our method to a large web col-
lection, we also investigate use of sampling to
reduce feature extraction time while maintain-
ing robust learning.}
}
@article{Carvalho10-forum,
  author = {Vitor Carvalho and Matthew Lease and Emine Yilmaz},
  title = {Crowdsourcing for Search Evaluation},
  journal = {ACM SIGIR Forum},
  volume = 44,
  number = 2,
  month = {December},
  year = 2010,
  pages = {17--22},
  url = {http://sigir.org/files/forum/2010D/sigirwksp/2010d_sigirforum_carvalho.pdf},
  confurl = {http://www.sigir.org/forum/2010D-TOC.html},
  abstract = {The Crowdsourcing for Search Evaluation Workshop (CSE 2010) was held on July 23,
2010 in Geneva, Switzerland, in conjunction with the 33rd Annual ACM SIGIR Conference.
The workshop addressed the latest advances in theory and empirical methods in crowdsourcing
for search evaluation, as well as novel applications of crowdsourcing for evaluating search
systems. Three invited talks were presented, along with seven refereed papers. Proceedings
from the workshop, along with presentation slides, have been made available online.}
}
@inproceedings{Cheng15-iconf,
  author = {James Cheng and Monisha Manoharan and Matthew Lease and Yan Zhang},
  title = {{Is there a Doctor in the Crowd? Diagnosis Needed! (for less than \$5)}},
  booktitle = {{Proceedings of the iConference}},
  url = {http://www.ischool.utexas.edu/~ml/papers/cheng-iconf15.pdf},
  year = {2015}
}
@inproceedings{Dang16-hcomp,
  title = {{MmmTurkey: A Crowdsourcing Framework for Deploying Tasks and Recording Worker Behavior on Amazon Mechanical Turk}},
  author = {Brandon Dang and Miles Hutson and Matthew Lease},
  booktitle = {{4th AAAI Conference on Human Computation and Crowdsourcing (HCOMP): Works-in-Progress Track}},
  year = {2016},
  url = {http://arxiv.org/abs/1609.00945},
  source = {https://github.com/CuriousG102/turkey},
  note = {3 pages. arXiv:1609.00945}
}
@inproceedings{Grady10,
  author = {Grady, Catherine  and  Lease, Matthew},
  title = {Crowdsourcing Document Relevance Assessment with Mechanical Turk},
  booktitle = {Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk},
  month = {June},
  year = {2010},
  address = {Los Angeles},
  publisher = {Association for Computational Linguistics},
  pages = {172--179},
  url = {http://www.aclweb.org/anthology/W10-0727},
  data = {http://www.ischool.utexas.edu/~ml/data/naacl-amt-2010.zip},
  confurl = {http://sites.google.com/site/amtworkshop2010},
  abstact = {We investigate human factors involved in designing
effective Human Intelligence Tasks
(HITs) for Amazon's Mechanical Turk. In
particular, we assess document relevance to
search queries via MTurk in order to evaluate
search engine accuracy. Our study varies four
human factors and measures resulting experimental
outcomes of cost, time, and accuracy
of the assessments. While results are largely
inconclusive, we identify important obstacles
encountered, lessons learned, related work,
and interesting ideas for future investigation.
Experimental data is also made publicly available
for further study by the community.}
}
@conference{Guo11-enir,
  author = {Lu Guo and Matthew Lease},
  title = {Personalizing Local Search with Twitter},
  booktitle = {{Workshop on Enriching Information Retrieval (ENIR) at the 34th Annual ACM SIGIR Conference}},
  year = {2011},
  url = {http://www.ischool.utexas.edu/~ml/papers/guo-enir11.pdf},
  note = {Oral presentation},
  confurl = {http://www.select.cs.cmu.edu/meetings/enir2011},
  video = {http://www.ischool.utexas.edu/~ml/papers/guo-enir11.wmv},
  source = {http://www.ischool.utexas.edu/~ml/papers/guo-enir11-sourcecode.zip}
}
@inproceedings{hale2006pcfgs,
  title = {PCFGs with syntactic and prosodic indicators of speech repairs},
  author = {Hale, John and Shafran, Izhak and Yung, Lisa and Dorr, Bonnie and Harper, Mary and Krasnyanskaya, Anna and Lease, Matthew and Liu, Yang and Roark, Brian and Snover, Matthew and others},
  booktitle = {Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics},
  pages = {161--168},
  year = {2006},
  organization = {Association for Computational Linguistics},
  url = {http://www.aclweb.org/anthology/P06-1021.pdf}
}
@techreport{Harper05,
  title = {{Parsing Speech and Structural Event Detection (PASSED): CLSP Summer Workshop Final Report}},
  author = {Mary Harper and Bonnie Dorr and John Hale and Brian Roark and Izhak Shafran and Matthew Lease and Yang
 Liu 
and Matthew Snover and Lisa Yunge and Anna Krasnyanskayai and Robin Stewart},
  institution = {Johns Hopkins University},
  year = {2005},
  confurl = {http://old-site.clsp.jhu.edu/ws2005/groups/eventdetect},
  slides = {http://old-site.clsp.jhu.edu/ws2005/groups/eventdetect/documents/FinalPresentation.pdf},
  url = {../papers/clsp05-finalreport.pdf}
}
@inproceedings{Johnson04-rtf,
  author = {Mark Johnson and Eugene Charniak and Matthew Lease},
  title = {An Improved Model For Recognizing Disfluencies in Conversational Speech},
  booktitle = {Rich Transcription 2004 Fall Workshop (RT-04F)},
  year = {2004},
  url = {../papers/rt04-paper.pdf}
}
@article{josephy2014workshops,
  title = {Workshops Held at the First AAAI Conference on Human Computation and Crowdsourcing: A Report},
  author = {Josephy, Tatiana and Lease, Matthew and Paritosh, Praveen and Krause, Markus and Georgescu, Mihai and Tjalve, Michael and Braga, Daniela},
  journal = {AI Magazine},
  volume = {35},
  number = {2},
  pages = {75--78},
  year = {2014},
  url = {../papers/CrowdScale2013.pdf}
}
@phdthesis{Jung-thesis15,
  author = {Hyun Joon Jung},
  title = {{Temporal Modeling Crowd Work for Quality Assurance in Crowdsourcing}},
  school = {School of Information, University of Texas at Austin},
  month = {December},
  year = 2015,
  url = {https://repositories.lib.utexas.edu/bitstream/handle/2152/33261/JUNG-DISSERTATION-2015.pdf}
}
@inproceedings{Jung15-hcomp,
  author = {Hyun Joon Jung and Matthew Lease},
  title = {{Modeling Temporal Crowd Work Quality with Limited Supervision}},
  booktitle = {{Proceedings of the 3rd AAAI Conference on Human Computation (HCOMP)}},
  year = {2015},
  pages = {83--91},
  url = {../papers/jung-hcomp15.pdf}
}
@inproceedings{Jung15-crowdml,
  author = {Hyun Joon Jung and Matthew Lease},
  title = {{Forecasting Crowd Work Quality via Multi-dimensional Features of Workers}},
  booktitle = {{ICML Workshop on Crowdsourcing and Machine Learning (CrowdML)}},
  year = {2015},
  url = {../papers/jung-crowdml15.pdf}
}
@inproceedings{Jung15-ecir,
  author = {Hyun Joon Jung and Matthew Lease},
  title = {{A Discriminative Approach to Predicting Assessor Accuracy}},
  booktitle = {{Proceedings of the 37th European Conference on Information Retrieval (ECIR)}},
  year = {2015},
  pages = {159-171},
  url = {../papers/ecir2015_hjung.pdf},
  note = {Received {\em Samsung Human-Tech Paper Award: Silver Prize in Computer Science.}}
}
@inproceedings{Jung14-hcomp,
  author = {Hyun Joon Jung and Yubin Park and Matthew Lease},
  title = {{Predicting Next Label Quality: A Time-Series Model of Crowdwork}},
  booktitle = {{Proceedings of the 2nd AAAI Conference on Human Computation (HCOMP)}},
  year = {2014},
  pages = {87--95},
  url = {../papers/hcomp14-jung.pdf}
}
@inproceedings{Jung14-www,
  author = {Hyun Joon Jung},
  title = {{Quality Assurance in Crowdsourcing via Matrix Factorization based Task Routing}},
  booktitle = {{Proceedings of World Wide Web (WWW) Ph.D. Symposium, Companion Publication}},
  year = {2014},
  pages = {3--8},
  confurl = {http://www2014.kr/calls/call-for-ph-d-symposium/},
  url = {../papers/jung-www14.pdf}
}
@techreport{Jung13-arxiv,
  title = {Crowdsourced Task Routing via Matrix Factorization},
  author = {Hyun Joon Jung and Matthew Lease},
  institution = {University of Texas at Austin},
  month = {October},
  day = {18},
  year = {2013},
  url = {http://arxiv.org/abs/1310.5142},
  note = {arXiv:1310.5142}
}
@techreport{Jung12-arxiv,
  title = {Evaluating Classifiers Without Expert Labels},
  author = {Hyun Joon Jung and Matthew Lease},
  institution = {University of Texas at Austin},
  month = {December},
  day = {5},
  year = {2012},
  url = {http://arxiv.org/pdf/1212.0960v1},
  note = {arXiv:1212.0960}
}
@inproceedings{Jung13-trec,
  author = {Hyun Joon Jung and Matthew Lease},
  title = {UT Austin in the TREC 2012 Crowdsourcing Track's Image Relevance Assessment Task},
  booktitle = {{Proceedings of the 21st NIST Text Retrieval Conference (TREC)}},
  url = {http://trec.nist.gov/pubs/trec21/papers/UTAustin.crowd.final.pdf},
  year = {2013}
}
@inproceedings{Jung11-crowdconf,
  author = {Hyun Joon Jung and Matthew Lease},
  title = {{Spam Worker Filtering and Featured-Voting based Consensus Accuracy Improvement}},
  booktitle = {{Proceedings of CrowdConf}},
  year = {2011},
  confurl = {http://www.crowdconf2011.com/posters.html},
  note = {Poster.}
}
@inproceedings{Jung11-hcomp,
  author = {Hyun Joon Jung and Matthew Lease},
  title = {{Improving Consensus Accuracy via Z-score and Weighted Voting}},
  booktitle = {{Proceedings of the 3rd Human Computation Workshop (HCOMP) at AAAI}},
  year = {2011},
  pages = {88--90},
  url = {http://www.ischool.utexas.edu/~ml/papers/jung-hcomp11.pdf},
  blog = {https://humancomputation.com/blog/?p=1206},
  confurl = {http://humancomputation.com/2011}
}
@inproceedings{Jung12-hcomp,
  author = {Hyun Joon Jung and Matthew Lease},
  title = {{Improving Quality of Crowdsourced Labels via Probabilistic Matrix Factorization}},
  booktitle = {{Proceedings of the 4th Human Computation Workshop (HCOMP) at AAAI}},
  year = {2012},
  pages = {101--106},
  confurl = {http://www.humancomputation.com/2012},
  url = {http://www.aaai.org/ocs/index.php/WS/AAAIW12/paper/download/5258/5609}
}
@inproceedings{Jung12-sigir,
  author = {Hyun Joon Jung and Matthew Lease},
  title = {{Inferring Missing Relevance Judgments from Crowd Workers via Probabilistic Matrix Factorization}},
  booktitle = {{Proceedings of the 35th international ACM SIGIR conference on Research and Development in Information Retrieval}},
  year = {2012},
  pages = {1095--1096},
  url = {../papers/jung-sigir12.pdf}
}
@inproceedings{kahn-EtAl:2005:HLTEMNLP,
  author = {Kahn, Jeremy G.  and  Lease, Matthew  and  Charniak, Eugene  and  Johnson, Mark  and  Ostendorf, Mari},
  title = {Effective Use of Prosody in Parsing Conversational Speech},
  booktitle = {Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (EMNLP'05)},
  month = {October},
  year = {2005},
  address = {Vancouver, British Columbia, Canada},
  publisher = {Association for Computational Linguistics},
  pages = {233--240},
  url = {http://cs.brown.edu/research/pubs/pdfs/2005/Kahn-2005-EUP.pdf}
}
@inproceedings{Kittur-cscw13,
  author = {Aniket Kittur and Jeff Nickerson and Michael S. Bernstein and Elizabeth Gerber and Aaron Shaw and John Zimmerman and Matthew Lease and John J. Horton},
  title = {The Future of Crowd Work},
  booktitle = {In Proceedings of the ACM Conference on Computer Supported Cooperative Work (CSCW)},
  pages = {1301--1318},
  month = {February},
  year = {2013},
  url = {http://ssrn.com/abstract=2190946},
  blog = {https://humancomputation.com/blog/?p=4799},
  note = {Social Science Research Network (SSRN) ID: 2190946}
}
@inproceedings{Klinger11-asist,
  author = {Jorn Klinger and Matthew Lease},
  title = {Enabling Trust in Crowd Labor Relations through Identity Sharing},
  booktitle = {Proceedings of the 74th Annual Meeting of the American Society for Information Science and Technology (ASIS\&T)},
  year = 2011,
  note = {Poster},
  url = {../papers/klinger-asist11.pdf},
  confurl = {http://www.asis.org/asist2011}
}
@inproceedings{Klinger11-crowdconf,
  author = {Jorn Klinger and Matthew Lease},
  title = {{Fighting Spam and Fraud in Online Labor Through Voluntary Identity Sharing}},
  booktitle = {{Proceedings of CrowdConf}},
  year = {2011},
  confurl = {http://www.crowdconf2011.com/posters.html},
  note = {Poster.}
}
@inproceedings{Kovashka10-crowdconf,
  author = {Kovashka, Adriana  and  Lease, Matthew},
  title = {Human and Machine Detection of Stylistic Similarity in Art},
  booktitle = {Proceedings of the 1st Annual Conference on the Future of Distributed Work (CrowdConf)},
  month = {September},
  year = {2010},
  address = {San Francisco},
  url = {../papers/kovashka-crowdconf10.pdf},
  confurl = {http://crowdconf.com},
  abstract = {
We describe methodology and evaluation for a new findsimilar
search task: the user specifies a source painting and
seeks other stylistically similar paintings, regardless of the
source painting.s subject (i.e. the object, person, or scene
depicted). We formulate this search as a content-based image
retrieval task, modeling stylistic similarity via detected
color, intensity in color changes, texture, and sharp points.
Additional features from machine vision are used for local
patches and the overall scene. To evaluate both the task
difficulty and system effectiveness, 90 people with varying
knowledge of art were asked to judge stylistic similarity between
different pairings of 240 paintings. To obtain these
judgments, we utilized Amazon Mechanical Turk, and we
discuss design issues involved in working with the platform
and controlling for quality in a crowdsourced setting. Results
of 3128 judgments show both task difficulty, with approximately
50% to 76.5% agreement between judges, and a
range of accuracies of system features vs. human judgments.
Most promising, features based on Leung-Malik filters
achieve roughly 80% agreement with knowledgeable judges.}
}
@mastersthesis{Kumar-thesis12,
  author = {Abhimanu Kumar},
  title = {{Supervised language models for temporal resolution of text in absence of explicit temporal cues}},
  school = {Department of Computer Science, University of Texas at Austin},
  month = {May},
  year = 2012,
  note = {Supervisor: Joydeep Ghosh.  Readers: Jason Baldridge and Matthew Lease.},
  url = {http://repositories.lib.utexas.edu/handle/2152/23581}
}
@techreport{Kumar12-arxiv,
  title = {Dating Texts without Temporal Cues},
  author = {Abhimanu Kumar and Jason Baldridge and Matthew Lease and Joydeep Ghosh},
  institution = {University of Texas at Austin},
  month = {November},
  day = {9},
  year = {2012},
  url = {http://arxiv.org/pdf/1211.2290v1},
  note = {arXiv:1211.2290}
}
@inproceedings{Kumar11-sigir,
  author = {Abhimanu Kumar and Matthew Lease},
  title = {Learning to Rank From a Noisy Crowd},
  booktitle = {{Proceedings of the 34th Annual ACM SIGIR Conference}},
  year = {2011},
  url = {http://www.ischool.utexas.edu/~ml/papers/kumar-sigir11.pdf},
  note = {Poster. Separately reviewed and accepted for encore presentation at the 3rd Human 
Computation Workshop (HCOMP) at AAAI 2011. Appears in SIGIR proceedings only.}
}
@inproceedings{Kumar11-cikm,
  title = {Supervised Language Modeling for Temporal Resolution of Texts},
  author = {Abhimanu Kumar and Matthew Lease and Jason Baldridge},
  booktitle = {{Proceeding of the 20th ACM Conference on Information and Knowledge Management (CIKM)}},
  year = {2011},
  pages = {2069-2072},
  url = {http://www.ischool.utexas.edu/~ml/papers/kumar-cikm11.pdf},
  note = {Poster.}
}
@inproceedings{Kumar11-csdm,
  author = {Abhimanu Kumar and Matthew Lease},
  title = {Modeling Annotator Accuracies for Supervised Learning},
  booktitle = {{Proceedings of the Workshop on Crowdsourcing for Search and Data Mining (CSDM) at the Fourth ACM International Conference on Web Search and Data Mining (WSDM)}},
  pages = {19--22},
  month = {February},
  day = {9},
  year = {2011},
  address = {Hong Kong, China},
  url = {http://ir.ischool.utexas.edu/csdm2011/proceedings/csdm2011_kumar.pdf},
  slides = {http://ir.ischool.utexas.edu/csdm2011/slides/kumar_csdm11_slides.pdf},
  confurl = {http://ir.ischool.utexas.edu/csdm2011/proceedings.html},
  abstract = {
Crowdsourcing methods are quickly changing the land-
scape for the quantity, quality, and type of labeled data
available to supervised learning. While such data can now
be obtained more quickly and cheaply than ever before, the
generated labels also tend to be far noisier due to limita-
tions of current quality control mechanisms and processes.
Given such noisy labels and a supervised learner, an impor-
tant question to consider, therefore, is how labeling effort
can be optimally utilized in order to maximize learner ac-
curacy? For example, should we (a) label additional unla-
beled examples, or (b) generate additional labels for labeled
examples in order to reduce potential label noise? In
comparison to prior work, we show faster learning can be
achieved for case (b) by incorporating knowledge of worker
accuracies into consensus labeling. Evaluation on four
binary classification tasks with simulated annotators shows
the empirical importance of modeling annotator accuracies.}
}
@article{Kutlu-2018,
  title = {{Learning to Effectively Select Topics For Information Retrieval Test Collections}},
  author = {Mucahid Kutlu and Tamer Elsayed and Matthew Lease},
  journal = {Information Processing and Management (IPM)},
  year = {2018},
  volume = 54,
  number = 1,
  pages = {37--59},
  publisher = {Elsevier},
  doi = {10.1016/j.ipm.2017.09.002},
  techreport = {https://arxiv.org/abs/1701.07810}
}
@inproceedings{Lease16-nieuw,
  title = {{Crowdsourcing for Success: Motivations, Design, \& Ethics}},
  author = {Matthew Lease},
  booktitle = {Workshop on Novel Incentives and Engineering Unique Workflows (NIEUW), organized by the Linguistic Data Consortium (LDC)},
  year = {2016},
  confurl = {https://www.ldc.upenn.edu/communications/workshops/nieuw-workshop},
  url = {../papers/lease-nieuw16.pdf}
}
@inproceedings{Lease16-medir,
  title = {{Systematic Review is e-Discovery in Doctor's Clothing}},
  author = {Matthew Lease and Gordon V.\ Cormack and Nguyen, An Thanh and Thomas A.\ Trikalinos and Byron C.\ Wallace},
  booktitle = {Proceedings of the Medical Information Retrieval (MedIR) Workshop at the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  year = {2016},
  url = {../papers/lease-medir16.pdf}
}
@article{Lease17-ency,
  author = {Lease, Matthew and Alonso, Omar},
  editor = {Alhajj, Reda and Rokne, Jon},
  title = {Crowdsourcing and Human Computation, Introduction},
  journal = {Encyclopedia of Social Network Analysis and Mining},
  year = {2017},
  publisher = {Springer},
  address = {New York, NY},
  pages = {1--12},
  isbn = {978-1-4614-7163-9},
  doi = {10.1007/978-1-4614-7163-9_107-1},
  url = {http://dx.doi.org/10.1007/978-1-4614-7163-9_107-1},
  note = {Same article Omar Alonso and I had published in the 2013 version of the encyclopedia, which they've re-released with other updates.}
}
@article{Lease13-ency,
  author = {Matthew Lease and Omar Alonso},
  title = {Crowdsourcing and Human Computation, Introduction},
  journal = {Encyclopedia of Social Network Analysis and Mining (ESNAM)},
  publisher = {Springer},
  month = {September},
  pages = {304--315},
  year = {2014},
  editors = {Reda Alhajj and Jon Rokne},
  url = {../papers/lease-esnam14.pdf},
  confurl = {http://link.springer.com/referenceworkentry/10.1007/978-1-4614-6170-8_107}
}
@article{Lease13-irj,
  author = {Matthew Lease and Emine Yilmaz},
  title = {{Crowdsourcing for Information Retrieval: Introduction to the Special Issue}},
  journal = {Information Retrieval},
  volume = 16,
  number = 2,
  month = {April},
  year = 2013,
  pages = {91-100},
  url = {http://link.springer.com/content/pdf/10.1007%2Fs10791-013-9222-7.pdf},
  confurl = {http://link.springer.com/journal/10791/16/2/}
}
@inproceedings{Lease-ssrn13,
  author = {Matthew Lease and Jessica Hullman and Jeffrey P.\ Bigham and Michael S.\ Bernstein and Juho Kim and Walter S. Lasecki and Saeideh Bakhshi and Tanushree Mitra and Robert C.\ Miller},
  title = {Mechanical Turk is Not Anonymous},
  booktitle = {Social Science Research Network (SSRN) Online},
  month = {March 6,},
  year = {2013},
  url = {http://ssrn.com/abstract=2228728},
  blog = {https://humancomputation.com/blog/?p=5177},
  note = {SSRN ID: 2228728}
}
@inproceedings{Lease11-trec,
  author = {Matthew Lease and Gabriella Kazai},
  title = {{Overview of the TREC 2011 Crowdsourcing Track (Conference 
Notebook)}},
  booktitle = {20th Text Retrieval Conference (TREC)},
  year = 2011,
  note = {Final proceedings version forthcoming.}
}
@inproceedings{Lease12-sigir-tutorial,
  author = {Lease, Matthew and Alonso, Omar},
  title = {Crowdsourcing for search evaluation and social-algorithmic search},
  booktitle = {Proceedings of the 35th international ACM SIGIR conference on Research and development in information retrieval},
  series = {SIGIR '12},
  year = {2012},
  isbn = {978-1-4503-1472-5},
  location = {Portland, Oregon, USA},
  pages = {1180--1180},
  numpages = {1},
  url = {http://doi.acm.org/10.1145/2348283.2348530},
  doi = {10.1145/2348283.2348530},
  acmid = {2348530},
  publisher = {ACM},
  address = {New York, NY, USA},
  keywords = {crowdsourcing, human computation},
  slides = {http://www.slideshare.net/mattlease/crowdsourcing-for-search-evaluation-and-socialalgorithmic-search},
  confurl = {http://www.sigir2011.org/crowdsourcing-for-information-retrieval.htm}
}
@book{crowdscale2013,
  editor = {Matthew Lease and Praveen Paritosh and Tatiana Josephy},
  title = {{Proceedings of the AAAI Human Computation Workshop on Crowdsourcing at Scale (CrowdScale)}},
  month = {November},
  day = {9},
  year = {2013},
  address = {Palm Springs, CA},
  publisher = {Online},
  confurl = {http://www.crowdscale.org/workshop-agenda/accepted-papers}
}
@book{Lease-CSE2010,
  editor = {Matthew Lease and Vitor Carvalho and Emine Yilmaz},
  title = {{Proceedings of the ACM SIGIR 2010 Workshop on Crowdsourcing for Search Evaluation (CSE 
2010)}},
  month = {July},
  day = {23},
  year = {2010},
  publisher = {Online},
  address = {Geneva, Switzerland},
  url = {http://ir.ischool.utexas.edu/cse2010/materials/CSE2010-Proceedings.pdf},
  confurl = {http://ir.ischool.utexas.edu/cse2010}
}
@inproceedings{Lease11-ijcnlp,
  author = {Matthew Lease},
  title = {{Crowd Computing: Opportunities and Challenges}},
  booktitle = {{Keynote at the 5th International Joint Conference on Natural Language Processing (IJCNLP)}},
  month = {November},
  day = {10},
  year = {2011},
  address = {Chiang Mai, Thailand},
  confurl = {http://www.ijcnlp2011.org},
  slides = {http://www.slideshare.net/mattlease/crowd-computing-opportunities-challenges-ijcnlp-2011-keynote}
}
@inproceedings{Lease11-hcomp,
  author = {Matthew Lease},
  title = {{On Quality Control and Machine Learning in Crowdsourcing}},
  booktitle = {{Proceedings of the 3rd Human Computation Workshop (HCOMP) at 
AAAI}},
  pages = {97--102},
  year = {2011},
  url = {http://www.ischool.utexas.edu/~ml/papers/lease-hcomp11.pdf},
  confurl = {http://www.humancomputation.com},
  note = {{Separately refereed and accepted for encore presentation at the AAAI Spring Sym
posium 2012: Wisdom of the Crowd.}}
}
@book{Lease-CIR2011,
  editor = {Matthew Lease and Emine Yilmaz and Alexander Sorokin and Vaughn Hester},
  title = {{Proceedings of the 2nd Workshop on Crowdsourcing for Information Retrieval at the 34th ACM International Conference on Information Retrieval (SIGIR 2011)}},
  month = {July},
  day = {28},
  year = {2011},
  address = {Beijing, China},
  publisher = {Online},
  confurl = {https://sites.google.com/site/cir2011ws/proceedings},
  url = {https://sites.google.com/site/cir2011ws/CIR2011Proceedings.pdf}
}
@book{Lease-CSDM2011,
  editor = {Matthew Lease and Vitor Carvalho and Emine Yilmaz},
  title = {{Proceedings of the Workshop on Crowdsourcing for Search and Data Mining (CSDM) at the Fourth ACM International Conference on Web Search and Data Mining (WSDM)}},
  month = {February},
  day = {9},
  year = {2011},
  address = {Hong Kong, China},
  publisher = {Online},
  confurl = {http://ir.ischool.utexas.edu/csdm2011/proceedings.html},
  url = {http://ir.ischool.utexas.edu/csdm2011/proceedings/csdm2011_proceedings.pdf}
}
@article{Lease11-forum,
  author = {Matthew Lease and Vitor Carvalho and Emine Yilmaz},
  title = {Crowdsourcing for Search and Data Mining},
  journal = {ACM SIGIR Forum},
  volume = 45,
  number = 1,
  month = {June},
  year = 2011,
  pages = {18--24},
  url = {http://sigir.org/files/forum/2011J/2011j_sigirforum_C_lease.pdf},
  confurl = {http://www.sigir.org/forum/2010D-TOC.html},
  abstract = {The Crowdsourcing for Search and Data Mining (CSDM 2011) workshop 
was held on February 9, 2011 in Hong Kong, China, in conjunction with the Fourth 
ACM International Conference on Web Search and Data Mining (WSDM 2011).
The workshop addressed recent advances in theory and empirical methods, as well as novel applications, in crowdsourcing for search and data 
mining. Three invited talks were presented, along with eight refereed papers. 
Workshop proceedings and presentation slides can be found online.}
}
@article{Lease11-forum2,
  author = {Matthew Lease and Emine Yilmaz},
  title = {Crowdsourcing for Information Retrieval},
  journal = {ACM SIGIR Forum},
  volume = 45,
  number = 2,
  month = {December},
  year = 2011,
  pages = {66--75},
  url = {http://sigir.org/files/forum/2011D/workshops/2011d_sigirforum_lease.pdf}
}
@phdthesis{Lease09-phd,
  author = {Matthew Lease},
  title = {{Beyond Keywords: Finding Information More Accurately and Easily Using Natural Language}},
  school = {Brown University Dept. of Computer Science},
  month = {August 24,},
  year = 2009,
  note = {Degree conferred May 2010},
  url = {http://cs.brown.edu/research/pubs/theses/phd/2010/lease.pdf}
}
@inproceedings{Lease09-trec,
  author = {Matthew Lease},
  title = {{Incorporating Relevance and Psuedo-relevance Feedback in the Markov Random Field Model: Brown at the TREC'08 Relevance 
Feedback Track}},
  booktitle = {Proceedings of the 17th Text Retrieval Conference (TREC'08)},
  year = 2009,
  note = {Best results in track. This paper supersedes an earlier version appearing in conference's Working Notes.},
  data = {../data/trec08.tar.bz2},
  url = {../papers/lease-trec08-proc.pdf},
  abstract = {We present a new document retrieval approach combining relevance feedback, pseudo-relevance feedback, and Markov random field modeling 
of term interaction. Overall effectiveness of our combined model and the relative contribution from each component is evaluated on the 
GOV2 webpage collection. Given 0-5 feedback documents, we find each component contributes unique value to the overall ensemble, 
achieving significant improvement individually and in combination. Comparative evaluation in the 2008 TREC Relevance Feedback track 
further shows our complete system typically performs as well or better than peer systems.}
}
@conference{Lease09-sigir,
  title = {{An Improved Markov Random Field Model for Supporting Verbose Queries}},
  author = {Matthew Lease},
  booktitle = {Proceedings of the 32nd Annual ACM SIGIR Conference},
  year = 2009,
  pages = {476--483},
  url = {../papers/lease-sigir09.pdf},
  abstract = {Recent work in supervised learning of term-based retrieval models has shown that significantly improved accuracy  can often be achieved in 
practice via better model estimation. In this paper, we show retrieval accuracy with the 
Markov random field (MRF) approach can be similarly improved via supervised estimation.  While the original MRF method 
estimates a parameter for each feature class from data, parameters within each class are set using the same fixed weighting scheme as the 
standard unigram. Because this scheme does not model context-sensitivity, its use particularly limits  retrieval accuracy with verbose 
queries. By employing supervised estimation instead, this deficit can be remedied. Retrieval experiments with verbose queries on three TREC 
document collections show our improved MRF consistently out-performs both the original MRF and the supervised unigram model. Additional 
experiments using blind-feedback and evaluation with optimal weighting demonstrate both the immediate value and further potential of more 
accurate MRF model estimation.}
}
@conference{Lease09-ecir,
  title = {{Regression Rank: Learning to Meet the Opportunity of Descriptive Queries}},
  author = {Matthew Lease and James Allan and W. Bruce Croft},
  booktitle = {Proceedings of the 31st European Conference on Information Retrieval (ECIR)},
  year = {2009},
  pages = {90--101},
  url = {../papers/lease-ecir09.pdf},
  data = {../data/mlease-ecir09-data.tar.bz2},
  abstract = {We present a new learning to rank framework for estimating context-sensitive term weights without use of feedback. Specifically, 
knowledge of effective term weights on past queries is used to estimate term weights for new queries. This generalization is achieved by 
introducing secondary features correlated with term weights and applying regression to predict term weights given features. To improve 
support for more focused retrieval like question answering, we conduct document retrieval experiments with TREC description queries on 
three document collections. Results show significantly improved retrieval accuracy.}
}
@inproceedings{Lease07-clef-proceedings,
  author = {Matthew Lease and Eugene Charniak},
  title = {A Dirichlet-smoothed Bigram Model for Retrieving Spontaneous Speech},
  booktitle = {Advances in Multilingual and Multimodal Information Retrieval: 8th Workshop of the Cross-Language Evaluation Forum, CLEF 2007, Revised Selected Papers},
  year = 2008,
  isbn = {978-3-540-85759-4},
  publisher = {Springer-Verlag},
  series = {Lecture Notes in Computer Science},
  volume = 5152,
  url = {../papers/mlease-clef2007.pdf}
}
@inproceedings{Lease07-clef,
  author = {Matthew Lease and Eugene Charniak},
  title = {Brown at {CL-SR}'07: Retrieving Conversational Speech in {E}nglish and {C}zech},
  booktitle = {Working Notes of the Cross-Language Evaluation Forum (CLEF): Cross-Language Speech Retrieval (CL-SR) track},
  year = 2007,
  note = {Corrected version},
  url = {../papers/leaseCLEF2007-corrected.pdf}
}
@inproceedings{Lease07-pikm,
  author = {Matthew Lease},
  title = {Natural Language Processing for Information Retrieval: the time is ripe (again)},
  booktitle = {Proceedings of the 1st Ph.D. Workshop at the ACM Conference on Information and Knowledge Management (PIKM)},
  year = 2007,
  note = {Best Paper award},
  url = {../papers/lease-pikm07.pdf},
  abstract = {Paraphrasing van Rijsbergen, the time is ripe for another attempt at using natural language processing (NLP) for 
information retrieval (IR). This paper introduces my dissertation study, which will explore methods for integrating modern NLP with 
state-of-the-art IR techniques. In addition to text, I will also apply retrieval to conversational speech data, which poses a unique set of 
considerations in comparison to text. Greater use of NLP has potential to improve both text and speech retrieval.}
}
@article{Lease06-sap,
  author = {Lease, Matthew and Johnson, Mark and Charniak, Eugene},
  title = {Recognizing disfluencies in conversational speech},
  journal = {IEEE Transactions on  Audio, Speech and Language Processing},
  volume = 14,
  number = 5,
  month = {September},
  year = 2006,
  pages = {1566-1573},
  url = {../papers/lease06-sap.pdf},
  abstract = {We present a system for modeling disfluency in conversational speech: repairs, fillers, and self-interruption points (IPs). For each sentence, candidate repair analyses are generated by a stochastic tree adjoining grammar (TAG) noisy-channel model. A probabilistic syntactic language model scores the fluency of each analysis, and a maximum-entropy model selects the most likely analysis given the language model score and other features. Fillers are detected independently via a small set of deterministic rules, and IPs are detected by combining the output of repair and filler detection modules. In the recent Rich Transcription Fall 2004 (RT-04F) blind evaluation, systems competed to detect these three forms of disfluency under two input conditions: a best-case scenario of manually transcribed words and a fully automatic case of automatic speech recognition (ASR) output. For all three tasks and on both types of input, our system was the top performer in the evaluation.},
  keywords = {"Disfluency modeling", "natural language processing", "rich transcription", "speech processing"}
}
@inproceedings{Lease06aaai,
  author = {Matthew Lease and Eugene Charniak and Mark Johnson and David McClosky},
  title = {A Look At Parsing and Its Applications},
  booktitle = {Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI-06)},
  month = {16--20 July},
  year = {2006},
  url = {../papers/aaai06.pdf}
}
@inproceedings{lease-johnson:2006:HLT-NAACL06-Short,
  author = {Lease, Matthew  and  Johnson, Mark},
  title = {Early Deletion of Fillers In Processing Conversational Speech},
  booktitle = {Proceedings of the Human Language Technology Conference of the NAACL (HLT-NAACL'06), Companion Volume: Short Papers},
  month = {June},
  year = {2006},
  address = {New York City, USA},
  publisher = {Association for Computational Linguistics},
  pages = {73--76},
  url = {../papers/mlease_naacl06.pdf},
  note = {Version here corrects Table 2 in published version.}
}
@techreport{Lease05-tr,
  title = {Parsing and Disfluency Modeling},
  author = {Matthew Lease},
  institution = {Brown University Department of Computer Science},
  number = {CS-05-15},
  year = 2005,
  url = {http://www.cs.brown.edu/research/pubs/techreports/reports/CS-05-15.html}
}
@inproceedings{Lease05-icassp,
  author = {Matthew Lease and Eugene Charniak and Mark Johnson},
  title = {Parsing and its applications for conversational speech},
  booktitle = {Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'05)},
  month = {March 18 - March 23},
  year = {2005},
  volume = 5,
  pages = {961--964},
  url = {../papers/lease05-icassp.pdf},
  abstract = {This paper provides an introduction to recent work in statistical parsing and its applications for conversational speech, with particular emphasis on the relationship between parsing and detecting speech repairs. While historically parsing and repair detection have been studied independently, we present a line of research which has spanned the boundary between the two and demonstrated the efficacy of this synergistic approach. Our presentation highlights successes to date, remaining challenges, and promising future work.}
}
@inproceedings{Lease05-ijcnlp,
  author = {Lease, Matthew and Charniak, Eugene},
  title = {Parsing Biomedical Literature},
  booktitle = {Proceedings of the 2nd International Joint Conference on Natural Language Processing (IJCNLP'05)},
  editor = {R. Dale and K.-F. Wong and J. Su and O. Kwong},
  month = {October 11 - October 13},
  address = {Jeju Island, Korea},
  year = {2005},
  pages = {58 -- 69},
  publisher = {Springer-Verlag},
  series = {Lecture Notes in Computer Science (LNCS)},
  volume = 3651,
  url = {../papers/lease-ijcnlp05.pdf},
  data = {../data/parser-treebank.tgz},
  abstract = {We present a preliminary study of several parser adaptation techniques evaluated on the GENIA corpus of MEDLINE abstracts [1,2]. We begin by observing that the Penn Treebank (PTB) is lexically impoverished when measured on various genres of scientific and technical writing, and that this significantly impacts parse accuracy. To resolve this without requiring in-domain treebank data, we show how existing domain-specific lexical resources may be leveraged to augment PTB-training: part-of-speech tags, dictionary collocations, and named-entities. Using a state-of-the-art statistical parser [3] as our baseline, our lexically-adapted parser achieves a 14.2\% reduction in error. With oracle-knowledge of named-entities, this error reduction improves to 21.2\%.}
}
@conference{Lease03-icdcs,
  title = {{SmartElevator}: Revitalizing A Legacy Device through Inexpensive Augmentation},
  author = {Lease, Matthew and Eddon, Guy},
  booktitle = {Proceedings of the IEEE 23rd International Conference on Distributed Computing Systems (ICDCS): 3rd International Workshop on Smart Appliances and Wearable Computing},
  year = {2003},
  pages = {254 -- 259},
  url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1203563}
}
@inproceedings{Lease02,
  title = {{Plan-Aware Behavioral Modeling}},
  booktitle = {Adjunct Proceedings of 4th Intl. Conference on Ubiquitous Computing (UBICOMP)},
  author = {Matthew Lease},
  pages = {35--36},
  year = {2002},
  url = {http://www.ubicomp.org/ubicomp2002/ubicomp_adjunct_proceedings.pdf}
}
@techreport{Liu12-tr,
  author = {Di Liu and Matthew Lease and Rebecca Kuipers and Randolph 
Bias},
  title = {Crowdsourcing for Usability Testing},
  institution = {School of Information, University of Texas at Austin},
  month = {March},
  day = {7},
  year = {2012},
  url = {http://arxiv.org/pdf/1203.1468v2},
  note = {arXiv:1203.1468}
}
@inproceedings{Liu12-asist,
  author = {Di Liu and Ranolph Bias and Matthew Lease and Rebecca Kuipers},
  title = {Crowdsourcing for Usability Testing},
  booktitle = {Proceedings of the 75th Annual Meeting of the American Society for Information Science and Technology (ASIS\&T)},
  month = {October 28--31},
  year = 2012,
  techreport = {http://arxiv.org/abs/1203.1468},
  url = {../papers/liu-asist12.pdf}
}
@inproceedings{Mankar17-hcomp,
  title = {{Design Activism for Minimum Wage Crowd Work}},
  author = {Akash Mankar and Riddhi J.\ Shah and Matthew Lease},
  booktitle = {5th AAAI Conference on Human Computation and Crowdsourcing (HCOMP): Works-in-Progress Track},
  year = 2017,
  techreport = {https://arxiv.org/abs/1706.10097},
  source = {http://github.com/akash-mankar/DesignActivism},
  url = {../papers/mankar-hcomp17.pdf},
  note = {See extended technical report: arXiv 1706.10097.}
}
@inproceedings{McDonnell17-ijcai,
  title = {{The Many Benefits of Annotator Rationales for Relevance Judgments}},
  author = {Tyler McDonnell and Mucahid Kutlu and Tamer Elsayed and Matthew Lease},
  booktitle = {Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI): Sister Conference Best Paper Track},
  year = {2017},
  url = {../papers/mcdonnell-ijcai17.pdf},
  data = {http://github.com/tylermcdonnell/WhyIsThatRelevant},
  blog = {https://humancomputation.com/blog/?p=9483},
  slides = {../papers/mcdonnell-hcomp16-slides.pdf},
  pages = {4909--4913}
}
@inproceedings{McDonnell16-hcomp,
  author = {Tyler McDonnell and Matthew Lease and Mucahid Kutlu and Tamer Elsayed},
  title = {{Why Is That Relevant?\ Collecting Annotator Rationales for Relevance Judgments}},
  booktitle = {{Proceedings of the 4th AAAI Conference on Human Computation and Crowdsourcing (HCOMP)}},
  pages = {139--148},
  year = {2016},
  data = {http://github.com/tylermcdonnell/WhyIsThatRelevant},
  url = {../papers/mcdonnell-hcomp16.pdf},
  blog = {https://humancomputation.com/blog/?p=9483},
  slides = {../papers/mcdonnell-hcomp16-slides.pdf},
  note = {{\bf Best Paper Award}}
}
@conference{Momtazi-ecdl10,
  title = {{Effective Term Weighting for Sentence Retrieval}},
  author = {Saeedeh Momtazi and Matthew Lease and Dietrich Klakow},
  booktitle = {Proceedings of the 14th European Conference on Research and Advanced Technology for Digital Libraries (ECDL)},
  year = {2010},
  pages = {482--485},
  series = {Lecture Notes in Computer Science (LNCS)},
  publisher = {Springer-Verlag},
  volume = 6273,
  url = {../papers/SaeedehMomtazi-ECDL10.pdf}
}
@inproceedings{Nguyen17-acl,
  author = {Nguyen, An Thanh and Junyi Jessy Li and Ani Nenkova and Byron C.\ Wallace and Matthew Lease},
  title = {{Aggregating and Predicting Sequence Labels from Crowd Annotations}},
  booktitle = {{Proceedings of the 55th annual meeting of the Association for Computational Linguistics (ACL)}},
  year = {2017},
  url = {../papers/nguyen-acl17.pdf},
  source = {https://github.com/thanhan/seqcrowd-acl17},
  data = {https://github.com/yinfeiy/PICO-data},
  pages = {299--309}
}
@inproceedings{Nguyen16-hcomp,
  author = {Nguyen, An Thanh and Matthew Halpern and Byron C.\ Wallace and Matthew Lease},
  title = {{Probabilistic Modeling for Crowdsourcing Partially-Subjective Ratings}},
  booktitle = {{Proceedings of the 4th AAAI Conference on Human Computation and Crowdsourcing (HCOMP)}},
  year = {2016},
  pages = {149--158},
  source = {http://github.com/thanhan/subjective-crowd-hcomp16},
  data = {http://github.com/Matthalp/mobile-cpu-user-sat-data.git},
  blog = {https://humancomputation.com/blog/?p=9458},
  url = {../papers/nguyen-hcomp16.pdf}
}
@inproceedings{Nguyen16-uai,
  title = {A Correlated Worker Model for Grouped, Imbalanced and Multitask Data},
  author = {Nguyen, An Thanh and Byron C.\ Wallace and Matthew Lease},
  booktitle = {Proceedings of the 32nd International Conference on Uncertainty in Artificial Intelligence (UAI)},
  year = {2016},
  source = {https://github.com/thanhan/code-uai16},
  url = {../papers/nguyen-uai16.pdf}
}
@inproceedings{Nguyen15-hcomp,
  author = {Nguyen, An Thanh and Byron C.\ Wallace and Matthew Lease},
  title = {{Combining Crowd and Expert Labels using Decision Theoretic Active Learning}},
  booktitle = {{Proceedings of the 3rd AAAI Conference on Human Computation (HCOMP)}},
  year = {2015},
  pages = {120--129},
  url = {../papers/nguyen-hcomp15.pdf}
}
@techreport{Petuchowski14-arxiv,
  title = {TurKPF: TurKontrol as a Particle Filter},
  author = {Ethan Petuchowski and Matthew Lease},
  institution = {University of Texas at Austin},
  month = {April},
  day = {20},
  year = {2014},
  url = {http://arxiv.org/abs/1404.5078},
  note = {arXiv:1404.5078},
  source = {https://github.com/ethanp/crowdsourcing/tree/master/TurKPF}
}
@inproceedings{Roark06-icassp,
  author = {Roark, B. and Yang Liu and Harper, M. and Stewart, R. and Lease, M. and Snover, M. and Shafran, I. and Dorr, B. and Hale, J. and Krasnyanskaya, A. and Yung, L.},
  title = {Reranking for Sentence Boundary Detection in Conversational Speech},
  booktitle = {Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'06)},
  year = 2006,
  month = {May 14--19},
  pages = {545--548},
  url = {http://www.hlt.utdallas.edu/~yangl/papers/icassp2006.pdf},
  abstract = {We present a reranking approach to sentence-like unit (SU) boundary detection, one of the EARS metadata extraction tasks. Techniques for generating relatively small n-best lists with high oracle accuracy are presented. For each candidate, features are derived from a range of information sources, including the output of a number of parsers. Our approach yields significant improvements over the best performing system from the NIST RT-04F community evaluation.}
}
@inproceedings{Roark06-lrec,
  author = {Brian Roark and Mary Harper and Eugene Charniak and Bonnie Dorr and Mark Johnson and Jeremy G. Kahn and Yang Liu and Mari Ostendorf and John Hale and Anna Krasnyanskaya and Matthew Lease and Izhak Shafran and Matthew Snover and Robin Stewart and Lisa Yung},
  title = {SParseval: Evaluation Metrics for Parsing Speech},
  booktitle = {Fifth International Conference on Language Resources and Evaluation (LREC'06)},
  year = 2006,
  address = {Genoa, Italy},
  url = {http://www.lrec-conf.org/proceedings/lrec2006/pdf/116_pdf.pdf}
}
@inproceedings{Ryu13-enrich,
  author = {Hohyon Ryu and Matthew Lease},
  title = {Generating Automatic Keywords for  Conversational Speech ASR Transcripts},
  booktitle = {1st ACM SIGIR Workshop on the Exploration, Navigation and Retrieval of Information in Cultural Heritage (ENRICH)},
  year = 2013,
  url = {../papers/ryu-enrich13.pdf},
  note = {Poster}
}
@inproceedings{Ryu11-asist,
  author = {Hohyon Ryu and Matthew Lease},
  title = {Crowdworker Filtering with Support Vector Machine},
  booktitle = {Proceedings of the 74th Annual Meeting of the American Society for Information Science and Technology (ASIS\&T)},
  year = 2011,
  url = {../papers/ryu-asist11.pdf},
  note = {Poster}
}
@inproceedings{Ryu11-crowdconf,
  author = {Hohyon Ryu and Matthew Lease},
  title = {{SVM-based Instant Crowdworker Filtering}},
  booktitle = {{Proceedings of CrowdConf}},
  year = {2011},
  confurl = {http://www.crowdconf2011.com/posters.html},
  note = {Poster.}
}
@inproceedings{Ryu12-hypertext,
  title = {Finding and Exploring Memes in Social Media},
  author = {Hohyon Ryu and Matthew Lease and Nicholas Woodward},
  booktitle = {{Proceedings of the 23rd ACM Conference on Hypertext and 
Social Media}},
  year = {2012},
  pages = {295--304},
  organization = {ACM},
  source = {https://bitbucket.org/softbass/meme-extractor},
  demo = {http://odyssey.ischool.utexas.edu/mb},
  video = {http://www.youtube.com/watch?v=-Cvv5aVaVfI&feature=plcp},
  url = {http://www.ischool.utexas.edu/~ml/papers/ryu-ht12.pdf}
}
@inproceedings{Saha13,
  author = {Ripon Saha and Matthew Lease and Sarfraz Khurshid and Dewayne Perry},
  title = {{Improving Bug Localization using Structured Information Retrieval}},
  booktitle = {{Proceedings of the 28th IEEE/ACM International Conference on Automated Software Engineering (ASE)}},
  year = {2013},
  confurl = {http://ase2013.org},
  pages = {345--355},
  data = {../data/ASE2013-BLUiR-Detailed-Results.zip},
  url = {../papers/saha-ase13.pdf}
}
@mastersthesis{Sheshadri-thesis14,
  author = {Aashish Sheshadri},
  title = {{A Collaborative Approach to IR Evaluation}},
  school = {Department of Computer Science, University of Texas at Austin},
  month = {May},
  year = 2014,
  note = {Co-Supervisors: Kristen Grauman and Matthew Lease.},
  url = {../papers/aashish_thesis.pdf}
}
@inproceedings{Sheshadri13,
  author = {Aashish Sheshadri and Matthew Lease},
  title = {{SQUARE: A Benchmark for Research on Computing Crowd Consensus}},
  booktitle = {{Proceedings of the 1st AAAI Conference on Human Computation (HCOMP)}},
  year = {2013},
  pages = {156--164},
  url = {http://ir.ischool.utexas.edu/square/documents/sheshadri.pdf},
  data = {http://ir.ischool.utexas.edu/square/}
}
@inproceedings{Sheshadri13-mediaeval,
  author = {Aashish Sheshadri and Matthew Lease},
  title = {{SQUARE: Benchmarking Crowd Consensus at MediaEval}},
  booktitle = {{Proceedings of the MediaEval 2013 Multimedia Benchmark Workshop}},
  year = {2013},
  note = {CEUR Workshop (cuer-ws.org) Proceedings Vol-1043, ISSN 1613-0073},
  url = {http://ceur-ws.org/Vol-1043/mediaeval2013_submission_62.pdf},
  confurl = {http://www.multimediaeval.org/mediaeval2013/crowd2013/},
  data = {http://ir.ischool.utexas.edu/square/}
}
@techreport{Shira11,
  author = {Elben Shira and Matthew Lease},
  title = {Expert Search on Code Repositories},
  institution = {Department of Computer Science, University of Texas at Austin},
  number = {TR-11-42},
  month = {December},
  year = {2011},
  url = {http://apps.cs.utexas.edu/tech_reports/reports/tr/TR-2066.pdf},
  pages = {1--8}
}
@inproceedings{Shukla12-sigir,
  author = {Shilpa Shukla and Matthew Lease and Ambuj Tewari},
  title = {{Parallelizing ListNet Training using Spark}},
  booktitle = {{Proceedings of the 35th international ACM SIGIR conference on Research and Development in Information Retrieval}},
  year = {2012},
  pages = {1127--1128},
  source = {../data/shukla-sigir12-code.tar.gz},
  url = {http://www.ischool.utexas.edu/~ml/papers/shukla-sigir12.pdf}
}
@inproceedings{Smucker14-cstrack,
  author = {Mark Smucker and Gabriella Kazai and Matthew Lease},
  title = {{Overview of the TREC 2013 Crowdsourcing Track}},
  booktitle = {Proceedings of the 22nd NIST Text Retrieval Conference (TREC)},
  url = {http://www.ischool.utexas.edu/~ml/papers/smucker-trec13.pdf},
  confurl = {http://trec.nist.gov/pubs/trec22/t22.proceedings.html},
  year = 2014
}
@inproceedings{Smucker13-cstrack,
  author = {Mark Smucker and Gabriella Kazai and Matthew Lease},
  title = {{Overview of the TREC 2012 Crowdsourcing Track}},
  booktitle = {Proceedings of the 21st NIST Text Retrieval Conference (TREC)},
  year = 2013,
  url = {http://trec.nist.gov/pubs/trec21/papers/CROWD12.overview.pdf},
  confurl = {http://trec.nist.gov/pubs/trec21/t21.proceedings.html}
}
@inproceedings{Sun16-hcomp,
  title = {{Crowdsourcing Information Extraction for Biomedical Systematic Reviews}},
  author = {Yalin Sun and Pengxiang Cheng and Shengwei Wang and Hao Lyu and Matthew Lease and Iain Marshall and Byron C. Wallace},
  booktitle = {{4th AAAI Conference on Human Computation and Crowdsourcing (HCOMP): Works-in-Progress Track}},
  year = {2016},
  url = {http://arxiv.org/abs/1609.01017},
  note = {3 pages. arXiv:1609.01017}
}
@inproceedings{Suwaileh16,
  author = {Reem Suwaileh and Mucahid Kutlu and Nihal Fathima and Tamer Elsayed and Matthew Lease},
  title = {{ArabicWeb16: A New Crawl for Today's Arabic Web}},
  booktitle = {Proceedings of the 39th international ACM SIGIR conference on Research and development in Information Retrieval},
  pages = {673--676},
  year = {2016},
  url = {http://www.ischool.utexas.edu/~ml/papers/sigir16-arabicweb.pdf},
  data = {http://qufaculty.qu.edu.qa/telsayed/arabicweb16/}
}
@inproceedings{Tang11-cir,
  author = {Wei Tang and Matthew Lease},
  title = {Semi-Supervised Consensus Labeling for Crowdsourcing},
  booktitle = {{ACM SIGIR Workshop on Crowdsourcing for Information Retrieval (CIR)}},
  year = {2011},
  pages = {36--41},
  url = {http://www.ischool.utexas.edu/~ml/papers/tang-cir11.pdf},
  confurl = {https://sites.google.com/site/cir2011ws/program}
}
@inproceedings{Tian11-sigir,
  author = {Aibo Tian and Matthew Lease},
  title = {Active Learning to Maximize Accuracy vs. Effort in Interactive Information Retrieval},
  booktitle = {{Proceedings of the 34th international ACM SIGIR conference on Research and Development in Information Retrieval}},
  pages = {145--154},
  year = {2011},
  url = {http://www.ischool.utexas.edu/~ml/papers/tian-sigir11.pdf}
}
@inproceedings{Vakharia15-iconf,
  title = {{Beyond Mechanical Turk: An Analysis of Paid Crowd Work Platforms}},
  author = {Donna Vakharia and Matthew Lease},
  booktitle = {{Proceedings of the iConference}},
  techreport = {http://arxiv.org/pdf/1310.1672v1},
  url = {http://www.ischool.utexas.edu/~ml/papers/donna-iconf15.pdf},
  year = 2015
}
@techreport{Vakharia13-arxiv,
  title = {Beyond AMT: An Analysis of Crowd Work Platforms},
  author = {Donna Vakharia and Matthew Lease},
  institution = {University of Texas at Austin},
  month = {October},
  day = {7},
  year = {2013},
  url = {http://arxiv.org/pdf/1310.1672v1},
  note = {arXiv:1310.1672}
}
@mastersthesis{Wolfson-thesis12,
  author = {Stephen Wolfson},
  title = {{Crowdsourcing and the Law}},
  school = {School of Information, University of Texas at Austin},
  month = {May},
  year = 2012,
  note = {Supervisor: Matthew Lease.  Reader: James Howison.},
  url = {http://repositories.lib.utexas.edu/handle/2152/ETD-UT-2012-05-5748}
}
@inproceedings{Wolfson11-asist,
  author = {Stephen Wolfson and Matthew Lease},
  title = {Look Before You Leap: Legal Pitfalls of Crowdsourcing},
  booktitle = {Proceedings of the 74th Annual Meeting of the American Society for Information Science and Technology (ASIS\&T)},
  url = {http://www.ischool.utexas.edu/~ml/papers/wolfson-asist11.pdf},
  year = 2011,
  confurl = {http://www.asis.org/asist2011}
}
@techreport{Yang10-tr,
  author = {Eunho Yang and Pradeep Ravikumar and Matthew Lease},
  title = {{A new class of ranking functions for DCG-like evaluation metrics using conditional probability models}},
  institution = {Department of Computer Science, University of Texas at Austin},
  number = {AI14-02 (AI report)},
  month = {October 29},
  year = {2010},
  url = {http://apps.cs.utexas.edu/tech_reports/reports/ai/AI-2175.pdf},
  note = {8 pages.}
}
@article{zhang-irj18,
  title = {{Neural Information Retrieval: At the End of the Early Years}},
  author = {Kezban Dilek Onal and Ye Zhang and Ismail Sengor Altingovde and Md Mustafizur Rahman and Pinar Karagoz and Alex Braylan and Brandon Dang and Heng-Lu Chang and Henna Kim and Quinten McNamara and Aaron Angert and Edward Banner and Vivek Khetan 
and Tyler McDonnell and  An Thanh Nguyen and Dan Xu and Byron C.\ Wallace and Maarten de Rijke and Matthew Lease},
  journal = {Information Retrieval},
  year = {2018},
  publisher = {Springer},
  techreport = {https://arxiv.org/abs/1611.06792},
  note = {Springer. To appear.}
}
@techreport{zhang-arxiv16,
  author = {{Zhang}, Y. and {Mustafizur Rahman}, M. and {Braylan}, A. and 
	{Dang}, B. and {Chang}, H.-L. and {Kim}, H. and {McNamara}, Q. and 
	{Angert}, A. and {Banner}, E. and {Khetan}, V. and {McDonnell}, T. and 
	{Thanh Nguyen}, A. and {Xu}, D. and {Wallace}, B.~C. and {Lease}, M.
	},
  title = {{Neural Information Retrieval: A Literature Review}},
  institution = {University of Texas at Austin},
  year = 2016,
  month = {November},
  url = {https://arxiv.org/abs/1611.06792},
  slides = {http://www.slideshare.net/mattlease/deep-learning-for-information-retrieval-models-progress-opportunities},
  note = {ArXiv 1611.06792.}
}
@inproceedings{zhang-acl17-weight,
  author = {Ye Zhang and Matthew Lease and Byron C.\ Wallace},
  title = {{Exploiting Domain Knowledge via Grouped Weight Sharing with Application to Text Categorization}},
  booktitle = {{Proceedings of the 55th annual meeting of the Association for Computational Linguistics (ACL)}},
  year = {2017},
  url = {../papers/zhang-acl17.pdf},
  pages = {155--160},
  techreport = {https://arxiv.org/abs/1702.02535}
}
@inproceedings{Zhang-aaai17,
  author = {Ye Zhang and Matthew Lease and Byron Wallace},
  title = {Active Discriminative Text Representation Learning},
  booktitle = {{Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI)}},
  year = {2017},
  url = {http://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14174/14265},
  pages = {3386-3392},
  note = {Also accepted for encore presentation at the 2nd Workshop on Representation Learning for NLP (RepL4NLP) at the 55th Annual Meeting of the Association for Computational Linguistics (ACL).},
  confurl = {https://sites.google.com/site/repl4nlp2017/}
}
@inproceedings{Zhang-sigir14,
  author = {Yinglong Zhang and Jin Zhang and Matthew Lease and Jacek Gwizdka},
  title = {Multidimensional Relevance Modeling via Psychometrics and Crowdsourcing},
  booktitle = {{Proceedings of the 37th international ACM SIGIR conference on Research and Development in Information Retrieval}},
  pages = {435--444},
  year = {2014},
  data = {../data/zhang-sigir14-data.zip},
  url = {../papers/zhang-sigir14.pdf}
}
@inproceedings{Zheng-apccm17,
  author = {Xi Zheng and Akanksha Bansal and Matthew Lease},
  title = {Bullseye: Structured Passage Retrieval and Document Highlighting for Scholarly Search},
  booktitle = {{The Thirteenth Asia-Pacific Conference on Conceptual Modelling (APCCM), held as part of the Australasian Computer Science Week (ACSW) Multiconference}},
  year = {2017},
  isbn = {978-1-4503-4768-6},
  location = {Geelong, Australia},
  articleno = {32},
  numpages = {4},
  url = {http://doi.acm.org/10.1145/3014812.3014846},
  doi = {10.1145/3014812.3014846},
  acmid = {3014846},
  url = {../papers/Zheng-APCCM17.pdf},
  techreport = {https://arxiv.org/abs/1406.1875},
  confurl = {http://www.dsl.uow.edu.au/main/apccm2017/},
  note = {4 pages.}
}
@mastersthesis{Zhou-thesis15,
  author = {Haofeng Zhou},
  title = {{Crowdsourcing Construction of Information Retrieval Test Collections for Conversational Speech}},
  school = {School of Information, University of Texas at Austin},
  month = {May},
  year = 2015,
  note = {Reader: Byron Wallace},
  url = {https://repositories.lib.utexas.edu/bitstream/handle/2152/31916/ZHOU-THESIS-2015.pdf}
}
@inproceedings{Zhou13-sslud,
  author = {Haofeng Zhou and Dennis Baskov and Matthew Lease},
  title = {Crowdsourcing Transcription Beyond Mechanical Turk},
  booktitle = {AAAI HCOMP Workshop on Scaling Speech, Language Understanding and Dialogue through Crowdsourcing (SSLUD)},
  year = {2013},
  confurl = {http://faculty.washington.edu/mtjalve/HCOMP2013.Workshop.html},
  url = {../papers/zhou-sslud13.pdf}
}
@inproceedings{Zhou:2011:MOO:1940761.1940842,
  author = {Zhou, Yongyi and Broussard, Ramona and Lease, Matthew},
  title = {Mobile options for online public access catalogs},
  booktitle = {{Proceedings of the iConference}},
  year = {2011},
  isbn = {978-1-4503-0121-3},
  location = {Seattle, Washington},
  acmid = {1940842},
  publisher = {{ACM}},
  pages = {598--605},
  numpages = {8},
  video = {../papers/zhou-brossard-mut.avi},
  url = {http://www.ischool.utexas.edu/~ml/papers/zhou-iconf10.pdf},
  confurl = {http://www.ischools.org/iConference11/2011index}
}
@conference{Lamarca02,
  title = {{PlantCare: An Investigation in Practical Ubiquitous Systems}},
  booktitle = {Proceedings of the 4th International Conference on Ubiquitous Computing (UBICOMP)},
  author = {LaMarca, A. and Brunette, W. and Koizumi, D. and Lease, M. and Sigurdsson, S.B. and Sikorski, K. and Fox, D. and Borriello, G.},
  series = {LECTURE NOTES IN COMPUTER SCIENCE},
  volume = 2498,
  pages = {316--332},
  year = {2002},
  publisher = {Springer},
  url = {http://www.intel-research.net/Publications/Seattle/072320021545_76.pdf}
}
@inproceedings{Sigurdsson02,
  author = {Anthony LaMarca and Waylon Brunette and David Koizumi and Matthew Lease and Stefan B. Sigurdsson and Kevin Sikorski and Dieter Fox and Gaetano Borriello},
  booktitle = {Pervasive '02: Proceedings of the First International Conference on Pervasive Computing},
  title = {Making Sensor Networks Practical with Robots},
  year = {2002},
  pages = {152--166},
  publisher = {Springer-Verlag},
  series = {LECTURE NOTES IN COMPUTER SCIENCE},
  volume = 2414,
  url = {http://link.springer.com/content/pdf/10.1007%2F3-540-45866-2_13.pdf}
}
@conference{Kalet99,
  title = {{Anatomical information in radiation treatment planning}},
  author = {Kalet, I.J. and Wu, J. and Lease, M. and Austin-Seymour, M.M. and Brinkley, J.F. and Rosse, C.},
  booktitle = {Proceedings of the American Medical Informatics Association (AMIA) Fall Symposium},
  year = {1999},
  url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2232501/pdf/procamiasymp00004-0328.pdf}
}
@conference{Kalet98,
  title = {{Radiation Therapy Planning: an Uncommon Application of Lisp}},
  author = {Kalet, I.J. and Giansiracusa, R.S. and Wilcox, C. and Lease, M.},
  booktitle = {Proceedings of the Conference on the 40th Anniversary of Lisp},
  editor = {R. Gabriel},
  year = {1998},
  url = {../papers/lisp40yrs.pdf}
}

This file was generated by bibtex2html 1.94.