http://nlp.cs.pitt.edu/ The Natural Language Processing Laboratory at the University of Pittsburgh en-us 2007-08-13T08:18:08-05:00 http://nlp.cs.pitt.edu/archives/2007_08.html#000960 Detecting Arguing and Sentiment in Meetings This paper analyzes opinion categories like Sentiment and Arguing in meetings. We first annotate the categories manually. We then develop genre-specific lexicons using interesting function word combinations for detecting the opinions. We analyze... Talks nlplab 2007-08-13T08:18:08-05:00 http://nlp.cs.pitt.edu/archives/2007_07.html#000955 Details soon.... nlplab 2007-07-02T14:00:00-05:00 http://nlp.cs.pitt.edu/archives/2007_06.html#000952 In this paper we examine whether the student-to-tutor convergence of lexical and speech features is a useful predictor of learning in a corpus of spoken tutorial dialogs. This possibility is raised by the Interactive Alignment Theory, which suggests a... Talks nlplab 2007-06-18T08:39:59-05:00 http://nlp.cs.pitt.edu/archives/2007_06.html#000950 Abstracts etc. TBA... Talks hwa 2007-06-11T14:00:00-05:00 http://nlp.cs.pitt.edu/archives/2007_06.html#000946 Paper title: The Utility of a Graphical Representation of Discourse Structure in Spoken Dialogue Systems Authors: Mihai Rotaru and Diane J. Litman Abstract: In this paper we explore the utility of the Navigation Map (NM), a graphical representation of the... nlplab 2007-06-04T14:00:00-05:00 http://nlp.cs.pitt.edu/archives/2007_05.html#000951 Hierarchical Phrase-Based Translation with Suffix Arrays A major engineering challenge in statistical machine translation systems is the efficient representation of extremely large translation rulesets. In phrase-based models, this problem can be addressed by storing the training data in memory and... Talks hwa 2007-05-31T14:00:00-05:00 http://nlp.cs.pitt.edu/archives/2007_05.html#000949 Presenter: Ryoko TOKUHISA ( Toyota Central R&D Labs ) NOTE - THIS TALK WILL BE AT 12 NOON! I introduce the overview of the researches in Toyota Central Labs. We are developing the dialogue system for the car navigation system... Talks nlplab 2007-05-21T12:00:00-05:00 http://nlp.cs.pitt.edu/archives/2007_04.html#000941 Congratulations to Kate Forbes-Riley, Mihai Rotaru, Diane Litman, and Joel Tetrault, for getting a Best Paper Award (Late-Breaking News category) at NAACL-HLT 2007 for "Exploring Affect-Context Dependencies for Adaptive System Development"... News nlplab 2007-04-07T11:19:45-05:00 http://nlp.cs.pitt.edu/archives/2007_03.html#000932 CANDIDATE: Mihai Rotaru TITLE: Applications of Discourse Structure for Spoken Dialogue Systems WHEN: Tuesday, March 20, 1 pm WHERE: 5317 Sennott Hall (5th floor conference room) COMMITTEE MEMBERS: Diane J. Litman (advisor) Rebecca Hwa Carolyn P. Rosé Janyce M. Wiebe... Talks nlplab 2007-03-20T13:00:00-05:00 http://nlp.cs.pitt.edu/archives/2007_03.html#000930 Speaker: Swapna Somasundaran Room : Board room ( 6th floor - room 6329) Sennot Square Time : 9:00 am Practice talk for ICWSM-07. Abstract In this work, we explore the utility of attitude types for improving question answering (QA) on... Talks nlplab 2007-03-13T09:37:10-05:00 http://nlp.cs.pitt.edu/archives/2006_12.html#000831 Learning to Extract Proteins and their Interactions from Biomedical Text (2:00, Room 5313 Sensq) - NOTE UNUSUAL TIME AND ROOM... Talks nlplab 2006-12-08T16:56:34-05:00 http://nlp.cs.pitt.edu/archives/2006_11.html#000893 Greg received an Honorable Mention for CRA's Outstanding Undergraduate Award for 2007!... News nlplab 2006-11-30T14:01:48-05:00 http://nlp.cs.pitt.edu/archives/2006_11.html#000854 Speaker: Art Ward Experimental research has shown that human users will converge with dialog systems along many dimensions of speech, including those of acoustic/prosodic features and lexical choice. Other results suggest that speech convergence may provide a variety of benefits... nlplab 2006-11-27T09:22:12-05:00 http://nlp.cs.pitt.edu/archives/2006_11.html#000830 Speaker: Joel Tetreault Data sparsity is one of the major issues that NLP researchers always wrestle with. That is, does one have enough data to make reliable conclusions in an experiment? Using Reinforcement Learning to improve a spoken dialogue system... Talks nlplab 2006-11-13T10:24:41-05:00 http://nlp.cs.pitt.edu/archives/2006_09.html#000822 Speaker: Hua Ai Purpose: Prelim Exam Abstract: User simulation is used to generate large corpora for using reinforcement learning to automatically learn the best policy for spoken dialogue systems. Although this approach is becoming increasingly popular, the differences between simulated... nlplab 2006-09-25T11:49:03-05:00