Unsupervised Multilingual Learning for POS Tagging (2009)
Benjamin Snyder, Tahira Naseem, Jacob Eisenstein, Regina Barzilay
We demonstrate the effectiveness of multilingual learning for unsupervised part-of-speech tagging. The key hypothesis of multilingual learning is that by combining cues from multiple languages, the...
Learning Document-Level Semantic Properties from Free-text Annotations (2009)
Harr Chen, Jacob Eisenstein, Regina Barzilay
This paper demonstrates a new method for leveraging free-text annotations to infer semantic properties of documents. Free-text annotations are becoming increasingly abundant, due to the recent...
Bayesian Unsupervised Topic Segmentation (2009)
Jacob Eisenstein, Regina Barzilay
This paper describes a novel Bayesian approach to unsupervised topic segmentation. Unsupervised systems for this task are driven by lexical cohesion: the tendency of wellformed segments to induce a...
Learning Document-Level Semantic Properties from Free-text Annotations (2009)
Harr Chen, Jacob Eisenstein, Regina Barzilay
This paper demonstrates a new method for leveraging free-text annotations to infer semantic properties of documents. Free-text annotations are becoming increasingly abundant, due to the recent...
Gestural Cohesion for Topic Segmentation (2009)
Jacob Eisenstein, Regina Barzilay, All Davis
This paper explores the relationship between discourse segmentation and coverbal gesture. Introducing the idea of gestural cohesion, we show that coherent topic segments are characterized by...
Randomized Decoding for Selection-and-Ordering Problems (2008)
Pawan Deshp, Regina Barzilay, David R. Karger
The task of selecting and ordering information appears in multiple contexts in text generation and summarization. For instance, methods for title generation construct a headline by selecting and...
Incremental Text Structuring with Online Hierarchical Ranking (2008)
Erdong Chen, Benjamin Snyder, Regina Barzilay
Many emerging applications require documents to be repeatedly updated. Such documents include newsfeeds, webpages, and shared community resources such as Wikipedia. In this paper we address the task...
Automatic Processing of Spoken Dialogue in the Home Hemodialysis Domain (2008)
Ronilda Lacson, Regina Barzilay
Spoken medical dialogue is a valuable source of information, and it forms a foundation for diagnosis, prevention and therapeutic management. However, understanding even a perfect transcript of spoken...
Turning Lectures into Comic Books Using Linguistically Salient Gestures (2008)
Jacob Eisenstein, Regina Barzilay, All Davis
Creating video recordings of events such as lectures or meetings is increasingly inexpensive and easy. However, reviewing the content of such video may be time-consuming and difficult. Our goal is to...
Learning Document-Level Semantic Properties from Free-text Annotations (2008)
Harr Chen, Jacob Eisenstein, Regina Barzilay
This paper demonstrates a new method for leveraging unstructured annotations to infer semantic document properties. We consider the domain of product reviews, which are often annotated by their...
Gestural Cohesion for Topic Segmentation (2008)
Jacob Eisenstein, Regina Barzilay, All Davis
This paper explores the relationship between discourse structure and coverbal gesture. Using the idea of gestural cohesion, we show that coherent topic segments are characterized by homogeneous...
Finding Temporal Order in Discharge Summaries (2008)
Philip Bramsen, Pawan Deshp, Yoong Keok Lee, Regina Barzilay
A method for automatic analysis of time-oriented clinical narratives would be of significant practical import for medical decision making, data modeling and biomedical research. This paper proposes a...
Incremental Text Structuring with Online Hierarchical Ranking (2008)
Erdong Chen, Benjamin Snyder, Regina Barzilay
Many emerging applications require documents to be repeatedly updated. Such documents include newsfeeds, webpages, and shared community resources such as Wikipedia. In this paper we address the task...
Gesture in Automatic Discourse Processing (2008)
Jacob Eisenstein, Regina Barzilay
Computers cannot fully understand spoken language without access to the wide range of modalities that accompany speech. This thesis addresses the particularly expressive modality of hand gesture, and...
Discourse topic and gestural form (2008)
Jacob Eisenstein, Regina Barzilay, All Davis
Coverbal gesture provides a channel for the visual expression of ideas. While some gestural emblems have culturally predefined forms (e.g., “thumbs up”), the relationship between gesture and...
Lexical Chains for Summarization (2007)
Sc Degree Of, Advisor Dr. Michael Elhadad, Regina Barzilay, Regina Barzilay
This thesis investigates one technique to produce a summary of an original text without requiring its full semantic interpretation, but instead relying on a model of the topic progression in the text...
We consider the problem of modeling the content structure of texts within a specific domain, in terms of the topics the texts address and the order in which these topics appear. We first present an...
Abstract Using Lexical Chains for Text Summarization (2007)
We investigate one techmque to produce a summary of an original text without requmng zts full seman-ttc interpretation, but instead relying on a model of the topic progresston m the text derived from...
Rik De Busser, Regina Barzilay, Paul Clough, Bruce Croft, Norbert Fuhr, Fredric Gey, ...
In cooperation with: Interdisciplinary Centre for Law and IT Research Group Legal Informatics & Information Retrieval IWT Vlaanderen Proceedings editors
Kathleen R. Mckeown, Regina Barzilay, David Evans, Vasileios Hatzivassiloglou, Judith L. Klavans, Ani Nenkova, ...
Recently, there have been significant advances in several areas of language technology, including clustering, text categorization, and summarization. However, efforts to combine technology from these...
We address the text-to-text generation problem of sentence-level paraphrasing--- a phenomenon distinct from and more difficult than word- or phrase-level paraphrasing. Our approach applies...
An important component of any generation system is the mapping dictionary, a lexicon of elementary semantic expressions and corresponding natural language realizations. Typically, labor-intensive...
� �Ð ÓÖ��Ö Ó � �Ú�ÒØ × �Ò � Ó��×�ÓÒ Ì�� × ×ØÖ�Ø��Ý Û� × ��Ö�Ú��
A New Approach to Expert System Explanations (2007)
Barzilay, Regina, McCullough, Daryl, Rambow, Owen, DeCristofaro, Jonathan, Korelsky, Tanya, Lavoie, Benoit
Expert systems were one of the first applications to emerge from initial research in artificial intelligence, and the explanation of expert system reasoning was one of the first applications of...
Multiple Aspect Ranking for Opinion Analysis (2007)
Benjamin Snyder, Regina Barzilay, Arthur C. Smith, Benjamin Snyder
Multiple aspect ranking using the good grief algorithm (2007)
Benjamin Snyder, Regina Barzilay
We address the problem of analyzing multiple related opinions in a text. For instance, in a restaurant review such opinions may include food, ambience and service. We formulate this task as a...
Database-text alignment via structured multilabel classification (2007)
Benjamin Snyder, Regina Barzilay
This paper addresses the task of aligning a database with a corresponding text. The goal is to link individual database entries with sentences that verbalize the same information. By providing...
Decoding Algorithms for Complex Natural Language Tasks (2007)
Pawan Deshpande, Regina Barzilay
This thesis focuses on developing decoding techniques for complex Natural Language Processing (NLP) tasks. The goal of decoding is to find an optimal or near optimal solution given a model that...
Database-text alignment via structured multilabel classification (2007)
Benjamin Snyder, Regina Barzilay
This paper addresses the task of aligning a database with a corresponding text. The goal is to link individual database entries with sentences that verbalize the same information. By providing...
Making sense of sound: Unsupervised topic segmentation over acoustic input (2007)
Igor Malioutov, Alex Park, Regina Barzilay, James Glass
We address the task of unsupervised topic segmentation of speech data operating over raw acoustic information. In contrast to existing algorithms for topic segmentation of speech, our approach does...
Minimum cut model for spoken lecture segmentation (2006)
Igor Malioutov, Regina Barzilay
We consider the task of unsupervised lecture segmentation. We formalize segmentation as a graph-partitioning task that optimizes the normalized cut criterion. Our approach moves beyond localized...
Aggregation via set partitioning for natural language generation (2006)
The role of aggregation in natural language generation is to combine two or more linguistic structures into a single sentence. The task is crucial for generating concise and readable texts. We...
Ronilda C. Lacson, Regina Barzilay, William J. Long
Spoken medical dialogue is a valuable source of information for patients and caregivers. This work presents a first step towards automatic analysis and summarization of spoken medical dialogue. We...
Paraphrasing for Automatic Evaluation (2006)
David Kauchak, Regina Barzilay
This paper studies the impact of paraphrases on the accuracy of automatic evaluation. Given a reference sentence and a machine-generated sentence, we seek to find a paraphrase of the reference...
Modeling local coherence: An entity-based approach (2005)
This paper considers the problem of automatic assessment of local coherence. We present a novel entity-based representation of discourse which is inspired by Centering Theory and can be computed...
Collective content selection for concept-to-text generation (2005)
A content selection component determines which information should be conveyed in the output of a natural language generation system. We present an efficient method for automatically learning content...
Sentence fusion for multidocument news summarization (2005)
Regina Barzilay, Kathleen R. Mckeown
A system that can produce informative summaries, highlighting common information found in many online documents, will help Web users to pinpoint information that they need without extensive reading....
Skorochodko’s Text Types Chained Ringed Monolith Piecewise (2005)
Regina Barzilay, Stargazers Text(from Hearst
• Intro- the search for life in space • The moon’s chemical composition • How early proximity of the moon shaped it • How the moon helped life evolve on earth • Improbability of the...
6.881 Natural Language Processing, Fall 2004 (2004)
This course is a graduate level introduction to natural language processing, the primary concern of which is the study of human language from a computational perspective. The class will cover models...
6.881 Natural Language Processing, Fall 2004 (2004)
This course is a graduate level introduction to natural language processing, the primary concern of which is the study of human language from a computational perspective. The class will cover models...
Barzilay, Regina, Lee, Lillian
We consider the problem of modeling the content structure of texts within a specific domain, in terms of the topics the texts address and the order in which these topics appear. We first present an...
We consider the problem of modeling the content structure of texts within a specific domain, in terms of the topics the texts address and the order in which these topics appear. We first present an...
We consider the problem of modeling the content structure of texts within a specific domain, in terms of the topics the texts address and the order in which these topics appear. We first present an...
Lexical Cohesion and Coherence 2/34 (2004)
• DUC results: most of automatic summaries exhibit lack of coherence • Is it possible to automatically compute text coherence?
We consider the problem of modeling the content structure of texts within a specific domain, in terms of the topics the texts address and the order in which these topics appear. We first present an...
Integrating Categorization, Clustering, and Summarization for Daily News Browsing (2003)
Barzilay, Regina, Evans, David, Sigelman, Sergey
Recently, there have been significant advances in several areas of language technology, including clustering, text categorization, and summarization. However, efforts to combine technology from these...
Learning to Paraphrase: An Unsupervised Approach Using Multiple-Sequence Alignment (2003)
Barzilay, Regina, Lee, Lillian
We address the text-to-text generation problem of sentence-level paraphrasing -- a phenomenon distinct from and more difficult than word- or phrase-level paraphrasing. Our approach applies...
Information fusion for multidocument summarization: Paraphrasing and generation (2003)
The number and variety of online news sources makes it difficult for people to track the news concerning even a single event. Redundancy causes such tracking to be extremely time-consuming: multiple...
Sentence Alignment for Monolingual Comparable Corpora (2003)
We address the problem of sentence alignment for monolingual corpora, a phenomenon distinct from alignment in parallel corpora. Aligning large comparable corpora automatically would provide a...
Columbia at the document understanding conference 2003 (2003)
Ani Nenkova, Barry Schiffman, Andrew Schlaiker, Sasha Blair-goldensohn, Regina Barzilay, Sergey Sigelman, ...
based on the multi-document summarization system that we developed for DUC 2002 (McKeown et al., 2002). It uses different summarization strategies depending on the
2003. Information Fusion for Multidocument Summarization: Paraphrasing and Generation (2003)
Information Fusion for Multidocument
Columbia’s newsblaster: New features and future directions (demo (2003)
Kathleen Mckeown, Regina Barzilay, John Chen, David Elson, David Evans, Judith Klavans, ...
Columbia’s Newsblaster tracking and summarization system is a robust system that clusters news into events, categorizes events into broad topics and summarizes multiple articles on each event. Here...
Columbia’s newsblaster: New features and future directions (demo (2003)
Kathleen Mckeown, Regina Barzilay, John Chen, David Elson, David Evans, Judith Klavans, ...
Columbia’s Newsblaster tracking and summarization system is a robust system that clusters news into events, categorizes events into broad topics and summarizes multiple articles on each event. Here...
Sentence Alignment for Monolingual Comparable Corpora (2003)
Regina Barzilay Cornell, Regina Barzilay
We address the problem of sentence alignment for monolingual corpora, a phenomenon distinct from alignment in parallel corpora. Aligning large comparable corpora automatically would provide a...
Sentence Alignment for Monolingual Comparable Corpora (2003)
Regina Barzilay Cornell, Regina Barzilay
We address the problem of sentence alignment for monolingual corpora, a phenomenon distinct from alignment in parallel corpora. Aligning large comparable corpora automatically would provide a...
Columbia at the Document Understanding Conference 2003 (2003)
Ani Nenkova Barry, Barry Schiffman, Andrew Schlaiker, Sasha Blair-goldensohn, Regina Barzilay, Sergey Sigelman, ...
Introduction The Columbia Summarizer for DUC 2003, Task 2, is based on the multi-document summarization system that we developed for DUC 2002 (McKeown et al., 2002). It uses different summarization...
Sentence Alignment for Monolingual Comparable Corpora (2003)
Regina Barzilay Cornell, Regina Barzilay, Noemie Elhadad
We address the problem of sentence alignment for monolingual corpora, a phenomenon distinct from alignment in parallel corpora. Aligning large comparable corpora automatically would provide a...
Information fusion for multidocument summerization : paraphrasing and generation (2003)
Department: Computer Science.
Bootstrapping Lexical Choice via Multiple-Sequence Alignment (2002)
Barzilay, Regina, Lee, Lillian
An important component of any generation system is the mapping dictionary, a lexicon of elementary semantic expressions and corresponding natural language realizations. Typically, labor-intensive...
Bootstrapping lexical choice via multiple-sequence alignment (2002)
An important component of any generation system is the mapping dictionary, a lexicon of elementary semantic expressions and corresponding natural language realizations. Typically, labor-intensive...
Inferring strategies for sentence ordering in multidocument news summarization (2002)
Regina Barzilay, Noemie Elhadad, Kathleen R. Mckeown
The problem of organizing information for multidocument summarization so that the generated summary is coherent has received relatively little attention. While sentence ordering for single document...
Inferring strategies for sentence ordering in multidocument news summarization (2002)
Regina Barzilay, Noemie Elhadad, Kathleen R. Mckeown
The problem of organizing information for multidocument summarization so that the generated summary is coherent has received relatively little attention. While sentence ordering for single document...
Bootstrapping lexical choice via multiple-sequence alignment (2002)
Conf On Empirical, Regina Barzilay
An important component of any generation system is the mapping dictionary, a lexicon of elementary semantic expressions and corresponding natural language realizations.
The Columbia Multi-Document Summarizer for DUC 2002 (2002)
Kathleen Mckeown David, David Evans, Ani Nenkova, Regina Barzilay, Vasileios Hatzivassiloglou, Barry Schiffman, ...
this paper was supported by the Defense Advanced Research Projects Agency under TIDES grant NUU01-00-1-8919. Any opinions, findings, or recommendations are those of the authors and do not necessarily...
The Columbia Multi-Document Summarizer for DUC 2002 (2002)
Kathleen Mckeown, David Evans, Ani Nenkova, Regina Barzilay, Vasileios Hatzivassiloglou, Barry Schiffman, ...
Inferring strategies for sentence ordering in multidocument news summarization (2002)
Regina Barzilay, Noemie Elhadad, Kathleen R. Mckeown
The problem of organizing information for multidocument summarization so that the generated summary is coherent has received relatively little attention. While sentence ordering for single document...
Bootstrapping lexical choice via multiple-sequence alignment (2002)
An important component of any generation system is the mapping dictionary, a lexicon of elementary semantic expressions and corresponding natural language realizations. Typically, labor-intensive...
Simfinder: A flexible clustering tool for summarization (2001)
Vasileios Hatzivassiloglou, Judith L. Klavans, Melissa L. Holcombe, Regina Barzilay, Min-yen Kan, Kathleen R. Mckeown
We present a statistical similarity measuring and clustering tool, SIMFINDER, that organizes small pieces of text from one or multiple documents into tight clusters. By placing highly related text...
Columbia Multi-Document Summarization: Approach and Evaluation (2001)
Kathleen R. Mckeown, Vasileios Hatzivassiloglou, Regina Barzilay, Barry Schiffman, David Evans, Simone Teufel
Different forms of summarization are useful in different situations, depending on the intended
Extracting paraphrases from a parallel corpus (2001)
Regina Barzilay, Kathleen R. Mckeown
While paraphrasing is critical both for interpretation and generation of natural language, current systems use manual or semi-automatic methods to collect paraphrases. We present an unsupervised...
Columbia Multi-Document Summarization: Approach and Evaluation (2001)
Kathleen R. Mckeown, Regina Barzilay, David Evans, Vasileios Hatzivassiloglou, Simone Teufel
Dierent forms of summarization are useful in dierent situations, depending on the intended purpose of the summary and on the types of
Simfinder: A flexible clustering tool for summarization (2001)
Vasileios Hatzivassiloglou, Judith L. Klavans, Melissa L. Holcombe, Regina Barzilay, Min-yen Kan, Kathleen R. Mckeown
We present a statistical similarity measuring and clustering tool, SIMFINDER, that organizes small pieces of text from one or multiple documents into tight clusters. By placing highly related text...
Sentence Ordering in Multidocument Summarization (2001)
Regina Barzilay, Noemie Elhadad, Kathleen R. Mckeown
The problem of organizing information for multidocument summarization so that the generated summary is coherent has received relatively little attention. In this paper, we describe two naive ordering...
SIMFINDER: A Flexible Clustering Tool for Summarization (2001)
Vasileios Hatzivassiloglou Judith, Judith L. Klavans, Melissa L. Holcombe, Regina Barzilay, Min-yen Kan, Kathleen R. Mckeown
We present a statistical similarity measuring and clustering tool, SIMFINDER, that organizes small pieces of text from one or multiple documents into tight clusters. By placing highly related text...
Ordering circumstantials for multi-document summarization (2001)
Michael Elhadad, Yael Netzer, Regina Barzilay, Kathleen Mckeown
We address the problem of ordering several circumstantials when generating or revising a clause. This problem occurs in the context of a multi-document summarization system that relies on language...
Simfinder: A flexible clustering tool for summarization (2001)
Vasileios Hatzivassiloglou, Judith L. Klavans, Melissa L. Holcombe, Regina Barzilay, Min-yen Kan, Kathleen R. Mckeown
We present a statistical similarity measuring and clustering tool, SIMFINDER, that organizes small pieces of text from one or multiple documents into tight clusters. By placing highly related text...
The Rules Behind Roles: Identifying Speaker Role in Radio Broadcasts (2000)
Regina Barzilay, Michael Collins, Julia Hirschberg, Steve Whittaker
Previous work has shown that providing information about story structure is critical for browsing audio broadcasts. We investigate the hypothesis that Speaker Role is an important cue to story...
Information Fusion in the Context of Multi-Document Summarization (1999)
Regina Barzilay, Kathleen R. Mckeown
We present a method to automatically generate a concise summary by identifying and synthesizing similar elements across related text from a set of multiple documents. Our approach is unique in its...
Towards multidocument summarization by reformulation: Progress and prospects (1999)
Kathleen R. Mckeown, Judith L. Klavans, Vasileios Hatzivassiloglou, Regina Barzilay, Eleazar Eskin
By synthesizing information common to retrieved documents, multi-document summarization can help users of information retrieval systems to find relevant documents with a minimal amount of reading. We...
Information Fusion in the Context of Multi-Document Summarization (1999)
Regina Barzilay, Kathleen R. McKeown, Michael Elhadad
We present a method to automatically generate a concise summary by identifying and synthesizing similar elements across related text from a set of multiple documents. Our approach is unique in its...
Verbalization of High-Level Formal Proofs (1999)
Regina Barzilay, Robert L. Constable
We propose a new approach to text generation from formal proofs that exploits the high-level and interactive features of a tactic-style theorem prover. The design of our system is based on...
Information Fusion in the Context of Multi-Document (1999)
Summarization Regina Barzilay, Regina Barzilay, Kathleen R. Mckeown
We present a method to automatically generate a concise summary by identifying and synthesizing similar elements across related text from a set of multiple documents. Our approach is unique in its...
Towards Multidocument Summarization by Reformulation: (1999)
Progress And Prospects, Kathleen R. Mckeown, Judith L. Klavans, Vasileios Hatzivassiloglou, Regina Barzilay, Eleazar Eskin
By synthesizing information common to retrieved documents, multi-document summarization can help users of information retrieval systems to find relevant documents with a minimal amount of reading. We...
Towards Multidocument Summarization by Reformulation: Progress and Prospects (1999)
Kathleen Mckeown, Judith L. Klavans, Vasileios Hatzivassiloglou, Regina Barzilay, Eleazar Eskin
By synthesizing information common to retrieved documents, multi-document summarization can help users of information retrieval systems to find relevant documents with a minimal amount of reading. We...
Information Fusion in the Context of Multi-Document Summarization (1999)
Regina Barzilay, Kathleen R. Mckeown
We present a method to automatically generate a concise summary by identifying and synthesizing similar elements across related text from a set of multiple documents. Our approach is unique in its...
Towards multidocument summarization by reformulation: Progress and prospects (1999)
Kathleen R. Mckeown, Judith L. Klavans, Vasileios Hatzivassiloglou, Regina Barzilay, Eleazar Eskin
By synthesizing information common to retrieved documents, multi-document summarization can help users of information retrieval systems to find relevant documents with a minimal amount of reading. We...
Summarization Evaluation Methods: Experiments and Analysis (1998)
Hongyan Jing Dept, Hongyan Jing, Regina Barzilay, Kathleen Mckeown, Michael Elhadad
Two methods are used for evaluation of summarization systems: an evaluation of generated summaries against an "ideal" summary and evaluation of how well summaries help a person perform in a...
A New Approach to Expert System Explanations (1998)
Regina Barzilay, Daryl Mccullough, Owen Rambow, Jonathan Decristofaro, Tanya Korelsky, Benoit Lavoie, ...
this paper, we present a new approach to providing an expert system with an explanation facility. The approach comprises both software components and a methodology for assembling the components. The...
Summarization Evaluation Methods: Experiments and Analysis (1998)
Hongyan Jing, Regina Barzilay, Kathleen Mckeown, Michael Elhadad
Two methods are used for evaluation of summarization systems: an evaluation of generated summaries against an "ideal" summary and evaluation of how well summaries help a person perform in a...
Using lexical chains for text summarization (1997)
Regina Barzilay, Michael Elhadad
We investigate one technique to produce a summary of an original text without requiring its full semantic interpretation, but instead relying on a model of the topic progression in the text derived...
Using Lexical Chains for Text Summarization (1997)
Regina Barzilay, Michael Elhadad
We investigate one technique to produce a summary of an original text without requiring its full semantic interpretation, but instead relying on a model of the topic progression in the text derived...
Using Lexical Chains for Text Summarization (1997)
Regina Barzilay, Michael Elhadad
We investigate one technique to produce a summary of an original text without requiring its full semantic interpretation, but instead relying on a model of the topic progression in the text derived...
Lexical Chains for Summarization (1997)
Advisor Dr. Michael Elhadad, Regina Barzilay, Regina Barzilay
This thesis investigates one technique to produce a summary of an original text without requiring its full semantic interpretation, but instead relying on a model of the topic progression in the text...
Finding Temporal Order in Discharge Summaries
Bramsen, Philip, Deshpande, Pawan, Lee, Yoong Keok, Barzilay, Regina
A method for automatic analysis of time-oriented clinical narratives would be of significant practical import for medical decision making, data modeling and biomedical research. This paper proposes a...
Automatic Processing of Spoken Dialogue in the Home Hemodialysis Domain
Lacson, Ronilda, Barzilay, Regina
Spoken medical dialogue is a valuable source of information, and it forms a foundation for diagnosis, prevention and therapeutic management. However, understanding even a perfect transcript of spoken...