Cross-document relationship classification for (2009)
Dragomir R. Radev, Zhu Zhang, Jahna Otterbacher
text summarization
Steven Bird, Robert Dale, Bonnie J. Dorr, Bryan Gibson, Mark T. Joseph, Min-yen Kan, ...
The ACL Anthology is a digital archive of conference and journal papers in natural language processing and computational linguistics. Its primary purpose is to serve as a reference repository of...
Ahmed Hassan, Qian Diao, Dragomir R. Radev
We present new nearest neighbor methods for text classification and an evaluation of these methods against the existing nearest neighbor methods as well as other well-known text classification...
The North American Computational Linguistics Olympiad (NACLO) (2009)
Dragomir R. Radev, Lori S. Levin, Thomas E. Payne
NACLO is a competition whose goal is to expose high school students to the field of Linguistics, including Computational Linguistics and to serve as a talent search for future students and...
Chapter # Query Modulation for Web-based Question Answering (2009)
Dragomir R. Radev, Hong Qi, Zhiping Zheng, Sasha Blair-goldensohn, Zhu Zhang, Weiguo Fan, ...
Abstract: The web is now becoming one of the largest information and knowledge repositories. Many large scale search engines (Google, Fast, Northern Light, etc.) have emerged to help users find...
Chapter 18 Towards Answer-Focused Summarization Using Search Engines (2009)
Harris Wu, Dragomir R. Radev, Weiguo Fan
People query search engines to find answers to a variety of questions on the Internet. Search cost would have been greatly reduced if search engines could accept natural language questions as...
Lexical similarity can distinguish between automatic and manual translations (2008)
We consider the problem of identifying automatic translations from manual translations of the same sentence. Using two different similarity metrics (BLEU and Levenshtein edit distance), we found out...
Frederick A. Peck, Suresh K. Bhavnani, Marilyn H. Blackmon, Dragomir R. Radev
the use of natural language systems for fact identification:
Introducing meta-services for biomedical information extraction (2008)
Leitner, Florian, Krallinger, Martin, Rodriguez-Penagos, Carlos, Hakenberg, Jörg, Plake, Conrad, Kuo, Cheng-Ju, ...
Abstract We introduce the first meta-service for information extraction in molecular biology, the BioCreative MetaServer (BCMS; http://bcms.bioinfo.cnio.es/ ). This prototype platform is a joint...
Introducing meta-services for biomedical information extraction (2008)
Leitner, Florian, Krallinger, Martin, Rodriguez-Penagos, Carlos, Hakenberg, Jorg, Plake, Conrad, Kuo, Cheng-Ju, ...
We introduce the first meta-service for information extraction in molecular biology, the BioCreative MetaServer (BCMS; http://bcms.bioinfo.cnio.es/). This prototype platform is a joint effort of 13...
Chapter 18 Towards Answer-Focused Summarization Using Search Engines (2008)
Harris Wu, Dragomir R. Radev, Weiguo Fan
People query search engines to find answers to a variety of questions on the Internet. Search cost would have been greatly reduced if search engines could accept natural language questions as...
Siwei Shen, Dragomir R. Radev, Agam Patel, Günes Erkan
Multiple sequence alignment techniques have recently gained popularity in the Natural Language community, especially for tasks such as machine translation, text generation, and paraphrase...
Scientific Paper Summarization Using Citation Summary Networks (2008)
Qazvinian, Vahed, Radev, Dragomir R.
Quickly moving to a new area of research is painful for researchers due to the vast amount of scientific literature in each field of study. One possible way to overcome this problem is to summarize a...
ITR: Information Fusion Across Multiple Text Sources: A Common Theory (2008)
cross-document structure theory, multi-document summarization
LexNet: A Graphical Environment for Graph-Based NLP (2008)
Dragomir R. Radev, Günes Erkan, Siwei Shen, James P. Sweeney
This interactive presentation describes LexNet, a graphical environment for graph-based NLP developed at the University of Michigan. LexNet includes LexRank (for text summarization), biased LexRank...
Sample Query Recommendations How It Works (2008)
Xiaodong Shi, Dragomir R. Radev, Dragomir R. Radev
• Novice search engine users are contemplated with the difficulty in formulating precise queries that represent their information needs •Query logs capture explicit descriptions of users ’...
Arzucan Özgür, Dragomir R. Radev
The biomedical literature is growing rapidly. This increases the need for developing text mining techniques to automatically extract biologically important information such as protein-protein...
MEAD ReDUCs: Michigan at DUC 2003 (2008)
Dragomir R. Radev, Jahna Otterbacher, Hong Qi, Daniel Tam
We present the results of Michigan’s participation in DUC 2003. Using mean length-adjusted coverage, we obtained the best score of all systems on task 4- question-focused summaries.
Web-based Question Answering (panel) (2008)
Dragomir R. Radev, Brian Ulicny, Ask Jeeves
Early TREC-style Question Answering Systems were characterized by the following features: (a) the answer of the question was known to be included in a given local corpus, (b) the size of the small...
Computational Linkuistics: word triggers across hyperlinks (2008)
Dragomir R. Radev, Hong Qi, Daniel Tam, Adam Winkel
It is known that context words tend to be selftriggers, that is, the probability of a content word to appear more than once in a document, given that it already appears once, is significantly higher...
Towards Answer-Focused Summarization (2008)
Harris Wu, Dragomir R. Radev, Weiguo Fan
Abstract _ _ People query search engines to find answers to a variety of questions on the Internet. Search cost would have been greatly reduced if search engines could accept natural language...
MEAD ReDUCs: Michigan at DUC 2003 (2008)
Dragomir R. Radev, Jahna Otterbacher, Hong Qi, Daniel Tam
We present the results of Michigan’s participation in DUC 2003. Using mean length-adjusted coverage, we obtained the best score of all systems on task 4- question-focused summaries.
Siwei Shen, Dragomir R. Radev, Agam Patel, Günes Erkan
Multiple sequence alignment techniques have recently gained popularity in the Natural Language community, especially for tasks such as machine translation, text generation, and paraphrase...
LexNet: A Graphical Environment for Graph-Based NLP (2008)
Dragomir R. Radev, Günes Erkan, Anthony Fader, Patrick Jordan, Siwei Shen, James P. Sweeney
This interactive presentation describes LexNet, a graphical environment for graph-based NLP developed at the University of Michigan. LexNet includes LexRank (for text summarization), biased LexRank...
LexNet: A Graphical Environment for Graph-Based NLP (2008)
Dragomir R. Radev, Günes Erkan, Siwei Shen, James P. Sweeney
This interactive presentation describes LexNet, a graphical environment for graph-based NLP developed at the University of Michigan. LexNet includes LexRank (for text summarization), biased LexRank...
Abstract Generating Summaries of Multiple News Articles (2008)
Kathleen Mckeown, Dragomir R. Radev
We present a natural language system which summarizes a series of news articles on the same event. It uses sum-marization operators, identified through empirical analysis of a corpus of news...
Computational Linkuistics: word triggers across hyperlinks (2008)
Dragomir R. Radev, Hong Qi, Daniel Tam, Adam Winkel
It is known that context words tend to be selftriggers, that is, the probability of a content word to appear more than once in a document, given that it already appears once, is significantly higher...
Lexical similarity can distinguish between automatic and manual translations (2008)
We consider the problem of identifying automatic translations from manual translations of the same sentence. Using two different similarity metrics (BLEU and Levenshtein edit distance), we found out...
Arzucan Özgür, Dragomir R. Radev
The biomedical literature is growing rapidly. This increases the need for developing text mining techniques to automatically extract biologically important information such as protein-protein...
Siwei Shen, Dragomir R. Radev, Agam Patel, Günes Erkan
Multiple sequence alignment techniques have recently gained popularity in the Natural Language community, especially for tasks such as machine translation, text generation, and paraphrase...
Rendezvous A WWW Synchronization System Author: (2008)
With the proliferation of WWW−based documents and especially of those that are likely to be of interest to the users often, the concept of hotlists was created. By using hotlists, users are able to...
Towards Answer-Focused Summarization (2008)
Harris Wu, Dragomir R. Radev, Weiguo Fan
Abstract _ _ People query search engines to find answers to a variety of questions on the Internet. Search cost would have been greatly reduced if search engines could accept natural language...
Publishers/Association for Computational Linguistics. (2008)
José Abracos, Gabriel Pereira, Lopes Statistical, Inderjeet Mani, Mark Maybury, Kathy Mckeown, ...
Exploiting cross-document relations for multi-document evolving summarization.
Bibliography Published Papers by Dragomir R. Radev References (2008)
Dragomir R. Radev, Alfred Aho, Shih-fu Chang, Kathleen Mckeown, Dragomir Radev, James Allan, ...
retrieval and language modeling. SIGIR Forum, 37(1), March
Bibliography Published Papers by Dragomir R. Radev References (2008)
Dragomir R. Radev, Alfred Aho, Shih-fu Chang, Kathleen Mckeown, Dragomir Radev, James Allan, ...
retrieval and language modeling. SIGIR Forum, 37(1), March
Özgür, Arzucan, Vu, Thuy, Erkan, Günes, Radev, Dragomir R.
Motivation: Understanding the role of genetics in diseases is one of the most important aims of the biological sciences. The completion of the Human Genome Project has led to a rapid increase in the...
Dragomir R. Radev, John Prager, Valerie Samn
suspected answers to natural language questions using predictive annotation
Evelyne Tzoukermann, Dragomir R. Radev, William A. Gale
. This paper explores morpho-syntactic ambiguities for French to develop a strategy for part-of-speech disambiguation that a) reflects the complexity of French as an inflected language, b) optimizes...
I I I I I I I I I I I I I (2007)
Dragomir R. Radev, Hongyan Jing
I Centroid-based summarization of multiple documents: sentence extraction, utility-based evaluation, and user studies
Building a Generation Knowledge Source using (2007)
Internet-accessible Newswire, Dragomir R. Radev, Kathleen R. Mckeown
In this paper, we describe a method for automatic creation of a knowledge source for text generation using information ex-traction over the Internet. We present a prototype system called PROFILE...
Dragomir R. Radev, Weiguo Fan, Zhu Zhang
In this paper, we present our recent work on the development of a scalable personalized web-based multi-document summarization and recommendation system: WebInEssence. WebInEssence is designed to...
Dragomir R. Radev, Sasha Blair-goldensohn, Zhu Zhang, Sundara Raghavan
Abstract. In this paper we present NewsInEssence, a fully deployed digital news system. A user selects a current news story of interest which is used as a seed article by NewsInEssence to nd in real...
Dragomir R. Radev, Hong Qi, Zhiping Zheng, Sasha Blair-goldensohn, Weiguo Fan, John Prager
The web is now becoming one of the largest information and knowledge repositories. Many large scale search engines (Google, Fast, Northern Light, etc.) have emerged to help users find information. In...
Alfred V. Aho, Shih-fu Chang, Kathleen R. Mckeown, Dragomir R. Radev, John R. Smith, Kazi A. Zaman
Abstract. In this paper we describe an ongoing research
Getting answers to natural language questions on the web (2007)
Dragomir R. Radev, Kelsey Libner, Weiguo Fan
Most popular search engines are not designed for answering natural language questions. However, when we asked hundreds of natural language questions of nine...
Ra Manzi, David Yarowsky, Dragomir R. Radev, Dragomir R. Radev, ...
[43] Evelyne Tzoukermann and Dragomir R. Radev. Using word class for partof
We present a series of experiments to demonstrate the validity of Relative Utility (RU) as a measure for evaluating extractive summarizers. RU is applicable in both singledocument and multi-document...
MEAD ReDUCs: Michigan at DUC 2003 Dragomir R. Radev (2007)
Dragomir R. Radev, Jahna Otterbacher Hong, Hong Qi, Daniel Tam
We present the results of Michigan's participation in DUC 2003. Using mean length-adjusted coverage, we obtained the best score of all systems on task 4 - question-focused summaries. 1
Citation Analysis, Centrality, and the ACL Anthology (2007)
Mark Thomas Joseph, Dragomir R. Radev
We analyze the ACL Anthology citation network in an attempt to identify the most “central ” papers and authors using graph-based methods. Citation data was obtained using text extraction from the...
Citation analysis, centrality, and the acl anthology (2007)
Mark Thomas Joseph, Dragomir R. Radev
We analyze the ACL Anthology citation network in an attempt to identify the most “central ” papers and authors using graph-based methods. Citation data was obtained using text extraction from the...
Bibliography Published Papers by Dragomir R. Radev References (2007)
Dragomir R. Radev, Alfred Aho, Shih-fu Chang, Kathleen Mckeown, Dragomir Radev, Bruce Croft, ...
[5] Suresh Bhavnani, Karen Drabenstott, and Dragomir Radev. Towards a unified framework of IR tasks and strategies. In 2001 ASIST Annual
Kevin M. Quinn, Burt L. Monroe, Michael Colaresi, Michael H. Crespin, Dragomir R. Radev
DRAFT – Please do not cite without permission. In this paper, we describe a method for statistical learning from speech documents that we apply to the Congressional Record in order to gain new...
Probabilistic question answering on the Web (2005)
Radev, Dragomir R., Fan, Weiguo, Qi, Hong, Wu, Harris, Grewal, Amardeep
Web-based search engines such as Google and NorthernLight return documents that are relevant to a user query, not answers to user questions. We have developed an architecture that augments existing...
Using random walks for question-focused sentence retrieval (2005)
Jahna Otterbacher, Günes Erkan, Dragomir R. Radev
We consider the problem of questionfocused sentence retrieval from complex news articles describing multi-event stories published over time. Annotators generated a list of questions central to...
Using random walks for question-focused sentence retrieval (2005)
Jahna Otterbacher, Günes Erkan, Dragomir R. Radev
We consider the problem of questionfocused sentence retrieval from complex news articles describing multi-event stories published over time. Annotators generated a list of questions central to...
Using random walks for question-focused sentence retrieval (2005)
Jahna Otterbacher, Günes Erkan, Dragomir R. Radev
We consider the problem of questionfocused sentence retrieval from complex news articles describing multi-event stories published over time. Annotators generated a list of questions central to...
Using random walks for question-focused sentence retrieval (2005)
Jahna Otterbacher, Günes Erkan, Dragomir R. Radev
We consider the problem of questionfocused sentence retrieval from complex news articles describing multi-event stories published over time. Annotators generated a list of questions central to...
Using random walks for question-focused sentence retrieval (2005)
Jahna Otterbacher, Günes Erkan, Dragomir R. Radev
We consider the problem of questionfocused sentence retrieval from complex news articles describing multi-event stories published over time. Annotators generated a list of questions central to...
Peck, Frederick A., Bhavnani, Suresh K., Blackmon, Marilyn H., Radev, Dragomir R.
In prior work we observed that expert searchers follow well-defined search procedures in order to obtain comprehensive information on the Web. Motivated by that observation, we developed a prototype...
The University of Michigan at DUC 2004 (2004)
Günes Erkan, Dragomir R. Radev
We present the results of Michigan’s participation in DUC 2004. Our system, MEAD, ranked as one of the top systems in four of the five tasks. We introduce our new feature, LexPageRank, a new...
Lexrank: graph-based centrality as salience in text summarization (2004)
We introduce a stochastic graph-based method for computing relative importance of textual units for Natural Language Processing. We test the technique on the problem of Text Summarization (TS)....
Lexrank: graph-based centrality as salience in text summarization (2004)
We introduce a stochastic graph-based method for computing relative importance of textual units for Natural Language Processing. We test the technique on the problem of Text Summarization (TS)....
The University of Michigan at DUC 2004 (2004)
Günes Erkan, Dragomir R. Radev
We present the results of Michigan’s participation in DUC 2004. Our system, MEAD, ranked as one of the top systems in four of the five tasks. We introduce our new feature, LexPageRank, a new...
Lexrank: graph-based centrality as salience in text summarization (2004)
We introduce a stochastic graph-based method for computing relative importance of textual units for Natural Language Processing. We test the technique on the problem of Text Summarization (TS)....
Lexrank: Graph-based lexical centrality as salience in text summarization (2004)
We introduce a stochastic graph-based method for computing relative importance of textual units for Natural Language Processing. We test the technique on the problem of Text Summarization (TS)....
Lexrank: Graph-based lexical centrality as salience in text summarization (2004)
We introduce a stochastic graph-based method for computing relative importance of textual units for Natural Language Processing. We test the technique on the problem of Text Summarization (TS)....
Single-document and multi-document summary evaluation via relative utility (2003)
We present a series of experiments to demonstrate the validity of Relative Utility (RU) as a measure for evaluating extractive summarization systems. Like some other evaluation metrics, it compares...
Evaluation Challenges in Large-Scale Document Summarization (2003)
Dragomir R. Radev, Wai Lam, Arda Celebi, Simone Teufel, John Blitzer
We present a large-scale meta evaluation of eight evaluation measures for both single-document and multi-document summarizers. To this end we built a corpus consisting of (a) 100 Million automatic...
Evaluation challenges in large-scale document summarization (2003)
Dragomir R. Radev, Wai Lam, Arda Çelebi
We present a large-scale meta evaluation of eight evaluation measures for both single-document and multi-document summarizers. To this end we built a corpus consisting of (a) 100 Million automatic...
Getting answers to natural language questions on the Web (2002)
Radev, Dragomir R., Libner, Kelsey, Fan, Weiguo
Most popular search engines are not designed for answering natural language questions. However, when we asked hundreds of natural language questions of nine leading search engines, all retrieved at...
The University of Michigan at TREC2002: question answering and novelty tracks (2002)
Hong Qi, Jahna Otterbacher, Adam Winkel, Dragomir R. Radev
The University of Michigan participated in two evaluations this year. In the Question Answering Track, we entered three dierent versions of our system, NSIR, previously described in [1]. For the...
The University of Michigan at TREC2002: question answering and novelty tracks (2002)
Hong Qi, Jahna Otterbacher, Adam Winkel, Dragomir R. Radev
The University of Michigan participated in two evaluations this year. In the Question Answering Track, we entered three different versions of our system, NSIR, previously described in [1]. For the...
Revisions that improve cohesion in multidocument summaries: a preliminary study (2002)
Jahna C. Otterbacher, Dragomir R. Radev, Airong Luo
Extractive summaries produced from multiple source documents suffer from an array of problems with respect to text cohesion. In this preliminary study, we seek to understand what problems occur in...
Towards CST-Enhanced Summarization (2002)
Zhu Zhang, Sasha Blair-Goldensohn, Dragomir R. Radev
In this paper, we propose to enhance the process of automatic extractive multi-document text summarization by taking into account cross-document structural relationships as posited in Cross-document...
Introduction to the Special Issue on Summarization (2002)
Dragomir R. Radev, Eduard Hovy, Kathleen McKeown
As the amount of on-line information increases, systems that can automatically summarize one or more documents become increasingly desirable. Recent research has investigated types of summaries,...
Experiments in single and multidocument summarization using MEAD (2001)
In this paper, we describe four experiments in text summarization. The first experiment involves the automatic creation of 120 multi-document summaries and 308 single-document summaries from a set of...
Mining the web for answers to natural language questions (2001)
Dragomir R. Radev, Hong Qi, Zhiping Zheng, Sasha Blair-goldensohn, Weiguo Fan, John Prager
The web is now becoming one of the largest information and knowledge repositories. Many large scale search engines (Google, Fast, Northern Light, etc.) have emerged to help users find information. In...
Mining the web for answers to natural language questions (2001)
Dragomir R. Radev, Hong Qi, Zhiping Zheng, Sasha Blair-goldensohn, Weiguo Fan, John Prager
The web is now becoming one of the largest information and knowledge repositories. Many large scale search engines (Google, Fast, Northern Light, etc.) have emerged to help users find information. In...
Dragomir R. Radev, Sasha Blair-goldensohn, Zhu Zhang, Revathi Sundara Raghavan
NEWSINESSENCE is a system for finding, visualizing and summarizing a topic-based cluster of news stories. In the generic scenario for NEWSINESSENCE, a user selects a single news story from a news Web...
Experiments in single and multidocument summarization using MEAD (2001)
In this paper, we describe four experiments in text summarization. The first experiment involves the automatic creation of 120 multi-document summaries and 308 single-document summaries from a set of...
Dragomir R. Radev, Sasha Blair-goldensohn, Zhu Zhang, Revathi Sundara Raghavan
School of Information y
Experiments in single and multidocument summarization using MEAD (2001)
Dragomir R. Radev, Sasha Blair-goldensohn, Zhu Zhang
In this paper, we describe four experiments in text summarization. The first experiment involves the automatic creation of 120 multi-document summaries and 308 single-document summaries from a set of...
Mining the web for answers to natural language questions (2001)
Dragomir R. Radev, Hong Qi, Zhiping Zheng, Sasha Blair-goldensohn, Weiguo Fan, John Prager
The web is now becoming one of the largest information and knowledge repositories. Many large scale search engines (Google, Fast, Northern Light, etc.) have emerged to help users find information. In...
Dragomir R. Radev, Sasha Blair-goldensohn, Zhu Zhang, Sundara Raghavan
Abstract. In this paper we present NewsInEssence, a fully deployed digital news system. A user selects a current news story of interest which is used as a seed article by NewsInEssence to find in...
Mining the web for answers to natural language questions (2001)
Dragomir R. Radev, Hong Qi, Zhiping Zheng, Sasha Blair-goldensohn, Weiguo Fan, John Prager
The web is now becoming one of the largest information and knowledge repositories. Many large scale search engines (Google, Fast, Northern Light, etc.) have emerged to help users find information. In...
WebInEssence: a personalized web-based multi-document summarization and recommendation system (2001)
Dragomir R. Radev, Weiguo Fan, Zhu Zhang
In this paper, we present our recent work on the development of a scalable personalized web-based multi-document summarization and recommendation system: WebInEssence. WebInEssence is designed to...
Ranking suspected answers to natural language questions using predictive annotation (2000)
Radev, Dragomir R., Prager, John, Samn, Valerie
In this paper, we describe a system to rank suspected answers to natural language questions. We process both corpus and query using a new technique, predictive annotation, which augments phrases in...
Radev, Dragomir R., Jing, Hongyan, Budzikowska, Malgorzata
We present a multi-document summarizer, called MEAD, which generates summaries using cluster centroids produced by a topic detection and tracking system. We also describe two new techniques, based on...
One search engine or two for question-answering (2000)
John Prager, Eric Brown, Dragomir R. Radev, Krzysztof Czuba
We present here a preliminary analysis of the results of our runs in the Question Answering track of TREC9. We have developed a complete system, including our own indexer and search engine, GuruQA,...
Automatic summarization of search engine hit lists (2000)
We present our work on open-domain multi-document summarization in the framework of Web search. Our system, SNS (pronounced "essence"), retrieves documents related to an...
One search engine or two for question-answering (2000)
John Prager, Eric Brown, Dragomir R. Radev, Krzysztof Czuba
We present here a preliminary analysis of the results of our runs in the Question Answering track of TREC9. We have developed a complete system, including our own indexer and search engine, GuruQA,...
Kathleen R. McKeown, Dragomir R. Radev
This chapter describes a class of word groups that lies between idioms and free word combinations. Idiomatic expressions are those in which the semantics of the whole cannot be deduced from the...
Automatic summarization of search engine hit lists (2000)
We present our work on open-domain multi-document summarization in the framework of Web search. Our system, SNS (pronounced "essence"), retrieves documents related to an...
We introduce CST (cross-document structure theory), a paradigm for multidocument analysis. CST takes into account the rhetorical structure of clusters of related textual documents. We present a...
Automatic summarization of search engine hit lists (2000)
We present our work on open-domain multi-document summarization in the framework of Web search. Our system, SNS (pronounced “essence”), retrieves documents related to an unrestricted user query...
Papers by Dragomir R. Radev (2000)
Ra Manzi, David Yarowsky, Dragomir R. Radev, Dragomir R. Radev, ...
Linguistics. [33] Evelyne Tzoukermann and Dragomir R. Radev. Use of weighted nding new information in threaded news. Technical Report CUCS-026-99, Columbia University, 1999. [24] Dragomir R. Radev,...
Dragomir R. Radev, Hongyan Jing
We present a multi-document summarizer, called MEAD, which generates summaries using cluster centroids produced by a topic detection and tracking system. We also describe two new techniques, based on...
Kathleen R. Mckeown, Dragomir R. Radev
This chapter describes a class of word groups that lies between idioms and free word combinations. Idiomatic expressions are those in which the semantics of the whole cannot be deduced from the...
Under consideration for other conferences (specify)? NO We introduce CST (cross-document structure theory), a paradigm for multi-document analysis. CST takes into account the rhetorical structure of...
The abundance of newswire on the World-Wide Web has resulted in at least four major problems, which seem to presentthe most interesting challenges to users and researchers alike: size,heterogeneity,...
Topic Shift Detection - finding new information in threaded news (1999)
On-line sources of news typically follow aparticular pattern when presenting updates on a news event overtime. First, they produce a preliminary report on the event, and latersend out updates as the...
Frequently Asked Questions about Natural Language Processing - Second Edition (1999)
This is an attempt to put together a list of frequently (and not sofrequently) asked questions about Natural Language Processing andtheir answers. This document is in no way perfect or complete or...
Dragomir R. Radev, A Kambhatla, Yiming Ye, Catherine Wolf, Wlodek Zadrozny
In this paper, we propose using standard XML messaging interfaces between components of natural language dialog systems. We describe a stock trading and information access system, where XML is used...
A description of the CIDR system as used for TDT-2 (1999)
Dragomir R. Radev, Vasileios Hatzivassiloglou, Kathleen R. Mckeown
We describe several experimental parameters and a parallelization technique used in our online document clustering system, CIDR. These modifications were introduced into CIDR to reduce the running...
A description of the CIDR system as used for TDT-2 (1999)
Dragomir R. Radev, Vasileios Hatzivassiloglou, Kathleen R. Mckeown
We describe several experimental parameters and a parallelization technique used in our online document clustering system, CIDR. These modifications were introduced into CIDR to reduce the running...
A description of the CIDR system as used for TDT-2 (1999)
Dragomir R. Radev, Vasileios Hatzivassiloglou, Kathleen R. Mckeown
We describe several experimental parameters and a parallelization technique used in our online document clustering system, CIDR. These modifications were introduced into CIDR to reduce the running...
Topic shift detection - finding new information in threaded news (1999)
On-line sources of news typically follow a particular pattern when presenting updates on a news event over time. First, they produce a preliminary report on the event, and later send out updates as...
Dragomir R. Radev, Dragomir R. Radev, Dragomir R. Radev
information, highlighting agreements and contradictions among sources on the same topic. We have developed novel techniques and algorithms for combining data from multiple sources at the conceptual...
DSML: A Proposal for XML Standards for Messaging Between (1999)
Components Of Natural, Dragomir R. Radev, A Kambhatla, Yiming Ye, Catherine Wolf, Wlodek Zadrozny
In this paper, we propose using standard XML messaging interfaces between components of natural language dialog systems. We describe a stock trading and information access system, where XML is used...
Dragomir R. Radev, A Kambhatla, Yiming Ye, Catherine Wolf, Wlodek Zadrozny
In this paper, we propose using standard XML messaging interfaces between components of natural language dialog systems. We describe a stock trading and information access system, where XML is used...
A description of the CIDR system as used for TDT-2 (1999)
Dragomir R. Radev, Vasileios Hatzivassiloglou, Kathleen R. Mckeown
We describe several experimental parameters and a parallelization technique used in our online document clustering system, CIDR. These modifications were introduced into CIDR to reduce the running...
A description of the CIDR system as used for TDT-2 (1999)
Dragomir R. Radev, Vasileios Hatzivassiloglou, Kathleen R. Mckeown
We describe several experimental parameters and a parallelization technique used in our online document clustering system, CIDR. These modifications were introduced into CIDR to reduce the running...
This paper presents the results of a study on the semantic constraints imposed on lexical choice by certain contextual indicators. We show how such indicators are computed and how correlations...
Generating natural language summaries from multiple on-line sources (1998)
Dragomir R. Radev, Dragomir R. Radev, Dragomir R. Radev
The abundance of newswire on the World-Wide Web has resulted in at least four major problems, which seem to present the most interesting challenges to users and researchers alike: size,...
Generating natural language summaries from multiple on-line sources (1998)
Dragomir R. Radev, Kathleen R. Mckeown
We present a methodology for summarization of news about current events in the form of brief-ings that include appropriate background (historical) information. The system that we developed, SUMMONS,...
Use of Weighted Finite State Transducers in Part of Speech Tagging (1997)
Tzoukermann, Evelyne, Radev, Dragomir R.
This paper addresses issues in part of speech disambiguation using finite-state transducers and presents two main contributions to the field. One of them is the use of finite-state machines for part...
Tzoukermann, Evelyne, Radev, Dragomir R., Gale, William A.
This paper explores morpho-syntactic ambiguities for French to develop a strategy for part-of-speech disambiguation that a) reflects the complexity of French as an inflected language, b) optimizes...
Generating Natural Language Summaries from Multiple On-Line Sources (1997)
We present a methodology for summarization of newson current events. Our approach is included in a system, calledSUMMONS which presents news summaries to the user in a naturallanguage form along with...
Building a Generation Knowledge Source using Internet-Accessible Newswire (1997)
Radev, Dragomir R., McKeown, Kathleen R.
In this paper, we describe a method for automatic creation of a knowledge source for text generation using information extraction over the Internet. We present a prototype system called PROFILE which...
Use of Weighted Finite State Transducers in Part of Speech Tagging (1997)
Evelyne Tzoukermann, Dragomir R. Radev
This paper addresses issues in part of speech disambiguation using finite-state transducers and presents two main contributions to the field. One of them is the use of finite-state machines for part...
Use of Weighted Finite State Transducers in Part of Speech Tagging (1997)
Evelyne Tzoukermann, Dragomir R. Radev
This paper addresses issues in part of speech disambiguation using finite-state transducers and presents two main contributions to the field. One of them is the use of finite-state machines for part...
Generating Natural Language Summaries from Multiple On-Line Sources (1997)
We present a methodology for summarization of news on current events. Our approach is included in a system, called SUMMONS which presents news summaries to the user in a natural language form along...
Using word class for part-of-speech disambiguation (1996)
Evelyne Tzoukermann, Dragomir R. Radev
radev©cs, columbia, edu This paper presents a methodology for improving part-of-speech disambiguation using word classes. We build on earlier work for tagging French where we showed that statistical...
Using Word Class for Part-of-speech Disambiguation (1996)
Evelyne Tzoukermann, Dragomir R. Radev
This paper presents a methodology for improving part-of-speech disambiguation using word classes. We build on earlier work for tagging French where we showed that statistical estimates can be...
Combining linguistic knowledge and statistical learning in French part-of-speech tagging (1995)
Evelyne Tzoukermann, Dragomir R. Radev, William A. Gale
This paper presents a new part-of-speech tagger that takes into account both linguistic knowledge and statistical learning. Its novelty relies in several aspects: (a) a fully modular architecture...
Generating Summaries of Multiple News Articles (1995)
Kathleen Mckeown, Dragomir R. Radev
So That Nobody Has To Go To School If They Don't Want To by Roger Sipher A decline in standardized test scores is but the most recent indicator that American education is in trouble. One reason...
Combining Linguistic Knowledge and Statistical Learning in French Part-of-Speech Tagging (1995)
Evelyne Tzoukermann, Dragomir R. Radev, William A. Gale
This paper presents a new part-ofspeech tagger that takes into account both linguistic knowledge and statistical learning. Its novelty relies in several aspects: (a) a fully modular architecture that...
Combining linguistic knowledge and statistical learning in French part-of-speech tagging (1995)
Evelyne Tzoukermann, Dragomir R. Radev, William A. Gale
This paper presents a new part-of-speech tagger that takes into account both linguistic knowledge and statistical learning. Its novelty relies in several aspects: (a) a fully modular architecture...
Introducing meta-services for biomedical information extraction
Leitner, Florian, Krallinger, Martin, Rodriguez-Penagos, Carlos, Hakenberg, Jörg, Plake, Conrad, Kuo, Cheng-Ju, ...
We introduce the first meta-service for information extraction in molecular biology, the BioCreative MetaServer (BCMS; ). This prototype platform is a joint effort of 13 research groups and provides...
Özgür, Arzucan, Vu, Thuy, Erkan, Güneş, Radev, Dragomir R.
Motivation: Understanding the role of genetics in diseases is one of the most important aims of the biological sciences. The completion of the Human Genome Project has led to a rapid increase in the...