Workshop Paper Submission deadline: | March 30, 2007 (extended) |
Notification of acceptance: | April 23, 2007 |
Camera ready due: | May 6, 2007 |
Workshop Date: | June 28-29, 2007 |
FREE MEAL!! Cheese and wine will be served at the poster session on the first day (June 28). It will be followed by a dinner. All the participants are invited to the dinner at the hotel restaurant starting at 7pm. It is free of charge!!
Now, the full schedule is available at the ACL2007 page
We are happy to announce the invited talk will be given by Prof. Oren Etzioni about "Machine Reading and Open Information Extraction"
Welcome to the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing web site
This workshop will take place at the ACL 2007.
Please look at the "Call for papers" page for the detail of the workshop.
Recognizing and generating textual entailment and paraphrase are regarded as important technologies in a broad range of NLP applications, including machine translation, information retrieval, information extraction, summarization, question answering and text generation. Both textual entailment and paraphrasing address relevant aspects of natural language semantics. Entailment is a directional relation between two expressions in which one of them implies the other, whereas paraphrase is a relation in which two expressions convey essentially the same meaning. Indeed, paraphrase can be defined as bi-directional entailment. While it may be debatable how such semantic definitions can be made well-founded, in practice we have already seen evidence that such knowledge is essential for many applications.
There have been two lines of workshops in this field. One is a series of three workshops on paraphrasing -- in Tokyo 2001, in Sapporo at ACL-2003 and in Jeju at IJCNLP-2005.The other is the Workshop on Empirical Modeling of Semantic Equivalence and Entailment (at ACL-2005), and two workshops of the previous PASCAL Recognizing Textual Entailment (RTE) Challenges (2005 and 2006). We combine those two lines of similar effort together at this workshop in order to see the convergence of the field and exchange ideas among a wider audience. The workshop has two parts, one is the general session where submission is open, and the other is the concluding workshop of the 3rd PASCAL RTE Challenge. The program will include general session papers and selected presentations and a poster session of RTE-3 systems. See PASCAL RTE homepage for details about the RTE-3 challenge (with result submission deadline on March 12).
This CFP calls for papers for the general session. Any research topic related to textual entailment and paraphrasing in any language is welcome. More specifically, topics of interest include, but are not limited to:
Workshop Paper Submission deadline: | March 30, 2007 (extended) |
Notification of acceptance: | April 23, 2007 |
Camera ready due: | May 6, 2007 |
Workshop Date: | June 28 (afternoon) - 29, 2007 |
Schedule overview
June 28 (Day 1) --------------- 2:00-2:05 Introduction 2:05-2:30 RTE Introduction & Overview 2:30-3:45 presentation (3x25min) 4:15-4:40 presentation (1x25min) 4:40-5:10 RTE Poster booster (2 min presentation for each) 5:10-6:15 RTE poster (65min; with wine and cheese) June 29 (Day 2) --------------- 9:00-10:15 presentation (3x25min) 10:15-10:45 pilot task overview 11:15-12:05 presentation (2x25min) 12:05-1:00 Invited talk (55min) 2:30-3:45 presentation (3x25min) 4:15-5:30 presentation (3x25min) 5:30-6:15 Open Discussion (45min)
Invited Talk
Speaker: Prof. Oren Etzioni Title: Machine Reading and Open Information Extraction Abstract: Is it possible to acquire a massive body of high-quality knowledge from the Web? My talk will describe our KnowItAll research project, which has been investigating this and related questions over the last five years. We have scaled and generalized information extraction methods to process arbitrary Web text, and to handle unanticipated concepts, but many challenges remain. One of the most formidable challenges is moving from extracting isolated nuggets of information to capturing a coherent body of knowledge that can support automatic inference. Yet, textual entailment would seem to benefit from exactly the sort of knowledge we are attempting to extract. I hope that my talk will help to stimulate dialogue between information extraction and textual entailment researchers on these crucial problems. Bio: Oren Etzioni is a Professor of Computer Science at the University of Washington's Computer Science Department, and the founder and director of the university's Turing Center. He received his Ph.D. from Carnegie Mellon in 1990, and his B.A. from Harvard in 1986. Etzioni has authored of over 100 technical papers on topics ranging from intelligent agents to data mining and Web search. In 2005, he was awarded the IJCAI Distinguished Paper Award for "A Probabilistic Model of Redundancy in Information Extraction". He received a National Young Investigator Award in 1993, and was chosen as a AAAI Fellow a decade later. Etzioni is the founder of three companies. Most recently, he is the founder of Farecast (www.farecast.com), a company that utilizes data mining to inform consumers about the right time to buy their air tickets. His work has been featured in the New York Times, Wall Street Journal, NPR, SCIENCE, The Economist, TIME Magazine, Business Week, Newsweek, Discover Magazine, Forbes Magazine, Wired, and elsewhere.
Accepted Papers
General Session =============== Bill MacCartney and Christopher D. Manning: Natural Logic for Textual Inference Rodney D. Nielsen and Wayne Ward: A Corpus of Fine-Grained Entailment Relations Joao Cordeiro, Gael Dias and Guillaume Cleuziou: Biology Based Alignments of Paraphrases for Sentence Compression Atsushi Fujita, Shuhei Kato, Naoki Kato and Satoshi Sato: A Compositional Approach toward Dynamic Phrasal Thesaurus Michael Ellsworth and Adam Janin: Mutaphrase: Paraphrasing with FrameNet Marilisa Amoia and Claire Gardent: A first order semantic approach to adjectival inference RTE session oral presentations ============================== Nathanael Chambers, Daniel Cer, Trond Grenager, David Hall, Chloe Kiddon, Bill MacCartney, Marie-Catherine de Marneffe, Daniel Ramage, Eric Yeh and Christopher D. Manning: Learning Alignments and Leveraging Natural Logic Andrew Hickl and Jeremy Bensley: A Discourse Commitment-Based Framework for Recognizing Textual Entailment Adrian Iftene and Alexandra Balahur-Dobrescu: Hypothesis Transformation and Semantic Variability Rules Used in Recognizing Textual Entailment Aljoscha Burchardt, Nils Reiter, Stefan Thater and Anette Frank: A Semantic Approach to Textual Entailment: System Evaluation and Task Analysis Daniel Bobrow, Dick Crouch, Tracy Halloway King, Cleo Condoravdi, Lauri Karttunen, Rowan Nairn, Valeria de Paiva and Annie Zaenen: Linguistically-focused Textual Entailment Roy Bar-Haim, Ido Dagan, Iddo Greental, Idan Szpektor and Moshe Friedman: Semantic Inference at the Lexical-Syntactic Level for Textual Entailment Recognition Baoli LI, Joseph Irwin, Ernest Garcia and Ashwin Ram: III University at the Third Recognizing Textual Entailment Challenge Stefan Harmeling: An Extensible Probabilistic Transformation-based Approach to the Third Recognizing Textual Entailment Challenge Marta Tatu and Dan Moldovan: COGEX at RTE 3 RTE poster session ================== Rui Wang and Gunter Neumann: Applying Subsequence Kernels to Recognizing Textual Entailment Alvaro Rodrigo, Anselmo Penas, Jesus Herrera and Felisa Verdejo: Experiments of UNED at the Third Recognising Textual Entailment Challenge Gaston Burek and Christian Pietsch: SVO triple based Latent Semantic Analysis for recognising textual entailment Prodromos Malakasiotis and Ion Androutsopoulos: Learning Textual Entailment using SVMs and String Similarity Measures Oscar Ferrandez, Daniel Micol, Rafael Munoz and Manuel Palomar: A Perspective-Based Approach for Solving Textual Entailment Recognition Fabio Massimo Zanzotto, Marco Pennacchiotti and Alessandro Moschitti: Shallow Semantic in Fast Textual Entailment Rule Learners Arturo Montejo-Raez, Jose Manuel Perea, Fernando Martinez-Santiago, Miguel Angel Garcia-Cumbreras, Maite Martin Valdivia and Alfonso Urena-Lopez: Combining Lexical-Syntactic Information with Machine Learning for Recognizing Textual Entailment Dan Roth and Mark Sammons: Semantic and Logical Inference Model for Textual Entailment Daniel Ferres and Horacio Rodriguez: Machine Learning with Semantic-Based Distances Between Sentences for Textual Entailment Erwin Marsi, Emiel Krahmer and Wauter Bosma: Dependency-based paraphrasing for RTE Scott Settembre: Textual Entailment Using Univariate Density Model and Maximizing Discriminant Function Catherine Blake: The Role of Sentence Structure in Recognizing Textual Entailment Rodolfo Delmonte: Entailment and Anaphora Resolution in RTE3 Peter Clark, Phil Harrison, John Thompson, William Murray, Jerry Hobbs and Christiane Fellbaum: On the Role of Lexical and World Knowledge in RTE3 Rod Adams, Gabriel Nicolae, Cristina Nicolae and Sanda Harabagiu: Textual Entailment Through Extended Lexical Overlap and Lexico-Semantic Matching
General session paper submissions should not exceed 8 pages in length, meanwhile RTE3 reports should include up to 6 double column pages. Format requirments will be the same as for full papers of ACL07. See http://ufal.mff.cuni.cz/acl2007/styles/ for style files.
All paper must be written and presented in English.
Papers should be submitted as PDF file no later than March 30, 2007 (midnight on US Pacific time), via the following web site http://www.softconf.com/acl07/ACL07-WS9/submit.html