NLP@Pitt

Welcome!

The laboratory is co-directed by Diane Litman, Janyce Wiebe, and Rebecca Hwa. We are pursuing research in a wide range of natural language processing problems, including discourse and dialogue, spoken language processing, affective computing, natural language learning, statistical parsing, and machine translation.

The Intelligent Systems Program, a PhD graduate program in Artificial Intelligence at the University of Pittsburgh, is now accepting applications! For more informations, please see our admission requirements page. To apply, please fill out the online webform

[Supervised and Unsupervised Methods in Employing Discourse Relations for Improving Opinion Polarity Classification]

PRESENTER: Swapna Somasundaran

WHEN: Tuesday 6/30/9, 3-4 pm

WHERE: Senott Square Rm 6329

Abstract

This work investigates design choices in modeling a discourse scheme for improving opinion polarity classification. For this, two diverse global inference paradigms are used: a supervised collective classification framework and an unsupervised optimization framework. The approaches perform substantially better than the baseline, establishing the efficacy of both the methods and the underlying discourse scheme. We also present quantitative and qualitative analyses showing how the improvements are achieved. (This paper is to be presented at EMNLP-2009.)

[A Selected Tour of NLP in the British Isles]

PRESENTER: Prof. Diane Litman, CS & LRDC

WHEN: Tuesday 6/9/9, 3-4pm

ABSTRACT

I will first give an idiosyncratic overview of NLP in the UK, based on my visits to York, Oxford, Sheffield, Aberdeen, the Open U, Cambridge, Ulster, and Dublin City Universities during my sabbatical.

I will also briefly describe my joint research with Johanna Moore's group at the University of Edinburgh, which investigates whether previous findings and methods in the area of tutorial dialogue can be generalized across dialogue corpora that differ in domain (physics versus electricity), modality (spoken versus typed), and tutor type (human versus computer)

[Distinguishing Historical from Current Problems in Clinical Reports-‹Which Textual Features Help?>]

PRESENTER: Danielle Mowery, DBMI graduate student

Date and Time: Wednesday May 27 @ Noon

Venue:Senott Square Rm 6329

ABSTRACT

Determining whether a condition is historical or recent is important for accurate results in biomedicine. In this paper, we investigate four types of information found in clinical text that might be used to make this distinction. We conducted a descriptive, exploratory study using annotation on clinical reports to determine whether this temporal information is useful for classifying conditions as historical or recent. Our initial results suggest that few of these feature values can be used to predict temporal classification.

[ONYX: A System for the Semantic Analysis of Clinical Text]

Presenter: Prof. Wendy Chapman, DBMI

Date and Time: Wednesday May 27 @ Noon

ABSTRACT

This paper introduces ONYX, a sentence-level text analyzer that implements a number of innovative ideas in syntactic and semantic analysis. ONYX is being developed as part of a project that seeks to translate spoken dental examinations directly into chartable findings.
ONYX integrates syntax and semantics to a high degree. It interprets sentences using a combination of probabilistic classifiers, graphical unification, and semantically annotated grammar rules. In this preliminary evaluation, ONYX shows inter-annotator agreement scores with humans of 86% for assigning semantic types to relevant words, 80% for inferring relevant concepts from words, and 76% for identifying relations between concepts.

[A Selected Tour of NLP in the British Isles]

Venue: Senott Square Rm 6329

Presenter: Diane Litman - CS, LRDC

Date and Time: Tues 04/17/2009 @ 3-4 pm

ABSTRACT

I will first give an idiosyncratic overview of NLP in the UK, based on my visits to York, Oxford, Sheffield, Aberdeen, the Open U, Cambridge, Ulster, and Dublin City Universities during my sabbatical.

I will also briefly describe my joint research with Johanna Moore's group at the University of Edinburgh, which investigates whether previous findings and methods in the area of tutorial dialogue can be generalized across dialogue corpora that differ in domain (physics versus electricity), modality (spoken versus typed), and tutor type (human versus computer).

TBA

Venue: Senott Square Rm 6329

Presenter: Behrang Mohit - ISP

Date and Time: Tues 04/07/2009 @ 3-4 pm

TBA

[User Simulation for Spoken Dialog System Development]

Venue: Senott Square Rm 6329

Presenter: Hua Ai - ISP

Date and Time: Tues 03/31/2009 @ 3-4 pm

ABSTRACT

In my thesis study, I investigate how to evaluate and how to build user simulations to help dialog system development.When evaluating user simulations, I use both human judges and automatic evaluation measures to assess the simulation model qualities. When building user simulations, I examine three factors that impact simulation models in the tasks of dialog strategy learning and dialog system development. (This is a practice talk for Hua's postdoc interview.)

[Interactivity and Intertextuality in Online Discourse]

Venue: Senott Square Rm 6329

Presenter: Prof. Barbara Warnick - Department of Communication

Date and Time: Tues 3/17/9 @ 3-4 pm

ABSTRACT

Communication researchers during the last ten years have become progressively more interested in features of the online text that cognitively engage users in processing and responding to online text. This presentation will report on two studies by the author prior to publication of her 2007 book, "Rhetoric Online". The first, published by her and three authors in "The Journal of Computer-Mediated Communication," examined the effects on two forms of interactivity commonly found on political candidate Web sites. The first form, text-based interactivity, considered how site content was verbally and visually expressed. The second form, campaign-to-user interactivity, focused on features or mechanisms used to enable communication between site users and the campaign.

The second study is based on the author's chapter on intertextuality in "Rhetoric Online." The study defines intertextuality as a form of interreference among texts in which an already familiar text is invoked or played upon in a new textual context. Intertextuality makes use of resources in the larger intertext (the textual context in which the discourse appears) to involve users in active co-construction of the text¹s meaning. A number of contrasting examples of this phenomenon will be introduced and discussed, so that the kinds of variation in online intertextuality can be identified.

[Opinion is not only word-deep: discourse-level relations for opinion analysis] Swapna Somasundaran CS Dept. : Tuesday 3/10/2009 @ 3-4pm

VENUE: SENSQ 6329

ABSTRACT:

Opinion analysis focuses on extracting subjective expressions and sentiments from text. Large-scale availability of public opinion over the internet weblogs, review websites, discussion forums and face to face conversations has motivated a great amount of research in this area in recent times.

Much of the research in opinion analysis focuses on finding expressions that are opinion-indicators (for example, expressions like ³great², ³boring², or ³failed to kill the spirit²). We feel that such approaches can be augmented by discourse-level analysis of opinions. Discourse-level analysis allows opinion expressions in different parts of the discourse to be interpreted in an interdependent, coherent fashion and allows us to capture the varied ways in which people reveal their opinions.

In order to achieve discourse-level opinion analysis, we first develop a scheme to relate different opinion expressions in a discourse. We validate this design by showing that human annotators can reliably recognize the opinion relations. Then, we implement our scheme with a machine learning framework of collective inference to show that a computer¹s ability to recognize opinion expressions is indeed enhanced when the discourse level information is used. Finally, we show that, by performing feature engineering using a simple machine learning framework, the discourse-level opinion relations of our scheme can be automatically detected.

[Using Zipf Frequencies as a Representativeness Measure in Statistical Active Learning of Natural Language] Onur Cobanoglu: Tuesday 2/17/09 @3-4 pm

Venue: Senott Square Rm 6329

Active learning has proven to be a successful strategy in quick development of corpora to be used in training of statistical natural language parsers.
A vast majority of studies in this field has focused on estimating informativeness of samples; however, representativeness of samples is another important criterion to be considered in active learning.

We present a novel metric for estimating representativeness of sentences, based on a modification of Zipf's Principle of Least Effort. Experiments on WSJ corpus with a wide-coverage parser show that our method performs always at least as good as and generally significantly better than alternative representativeness-based methods.