home

Idan Szpektor - Home Page

I am a research scientist at Yahoo! Research Haifa. My main research interests are Natural Language Processing, Search Technologies, Text Mining and Social Networks.

I support:

• The research for a cure for ALS. You can read more about it at ISRALS.ORG.
• The fight for cancelling the Economic Arrangements Law. You can read more about it at LAHATS.ORG.
• Accessibility for handicaps and workers' rights via HATAV HAHEVRATI.

You can also view my LinkedIn profile.

Check out the Wiki site of Natural Language Processing in Israel.

Education

2009: PhD in Natural Language Processing at Bar-Ilan University under the supervision of Prof. Ido Dagan.

2005: Master of Science in Natural Language Processing (Summa Cum Laude). Tel Aviv University, Tel Aviv, Israel. Supervisors: Dr. Ido Dagan, Prof. Yossi Matias.

1997: Bachelor of Science in Mathematics and Computer Science (Magna Cum Laude). Tel Aviv University, Tel Aviv, Israel.

Publications

More recent publications can be found at my Yahoo Home Page.

Shachar Mirkin, Lucia Specia, Nicola Cancedda, Ido Dagan, Marc Dymetman and Idan Szpektor. 2009. Source-Language Entailment Modeling for Translating Unknown Terms. In Proceedings of ACL-IJCNLP 2009.

Lili Kotlerman, Ido Dagan, Idan Szpektor and Maayan Zhitomirsky-Geffet. 2009. Directional Distributional Similarity for Lexical Expansion. In Proceedings of ACL-IJCNLP 2009.

Idan Szpektor and Ido Dagan. 2009. Augmenting WordNet-based Inference with Argument Mapping. In Proceedings of TextInfer 2009.

Shachar Mirkin, Roy Bar-Haim, Ido Dagan, Eyal Shnarch, Asher Stern, Idan Szpektor, Jonathan Berant. 2009. Addressing Discourse and Document Structure in the RTE Search Task. In Proceedings of TAC 2009. (pdf)

Idan Szpektor and Ido Dagan. 2008. Learning Entailment Rules for Unary Templates. In Proceedings of COLING 2008 as a full oral paper. (pdf)

Idan Szpektor, Ido Dagan, Roy Bar-Haim and Jacob Goldberger. 2008. Contextual Preferences. In Proceedings of ACL 2008. (pdf)

Roy Bar-Haim, Jonathan Berant, Ido Dagan, Iddo Greental, Shachar Mirkin, Eyal Shnarch and Idan Szpektor. 2008. Efficient Semantic Deduction and Approximate Matching over Compact Parse Forests. In Proceedings of Text Analysis Conference (TAC) 2008.

Ido Dagan, Roy Bar-Haim, Idan Szpektor, Iddo Greental, and Eyal Shnarch. 2008. Natural Language as the Basis for Meaning Representation and Inference. In Proceedings of CICLING 2008 (pdf).

Idan Szpektor, Eyal Shnarch and Ido Dagan. 2007. Instance-based Evaluation of Entailment Rule Acquisition. In Proceedings of ACL 2007. (pdf)

Idan Szpektor and Ido Dagan. 2007. Learning Canonical Forms of Entailment Rules. In Proceedings of RANLP 2007. (pdf)

Idan Szpektor, Ido Dagan, Alon Lavie, Danny Shacham and Shuly Winter. 2007. Cross Lingual and Semantic Retrieval for Cultural Heritage Appreciation. In Proceedings of LaTeCH 2007. (pdf)

Roy Bar-Haim, Ido Dagan, Iddo Greental, Idan Szpektor and Moshe Fridman. 2007. Semantic Inference at the Lexical-Syntactic Level for Textual Entailment Recognition. In Proceedings of WTEP 2007, Prague. (pdf)

Roy Bar-Haim, Ido Dagan, Bill Dolan, Lisa Ferro, Danilo Giampiccolo, Bernardo Magnini and Idan Szpektor. 2006. The Second PASCAL Recognising Textual Entailment Challenge. In Proceedings of the Second PASCAL Recognising Textual Entailment Challenge. (pdf)

Lorenza Romano, Milen Kouylekov, Idan Szpektor, Ido Dagan and Alberto Lavelli. 2006. Investigating a Generic Paraphrase-based Approach for Relation Extraction. On Proceedings of EACL 2006. (pdf)

Roy Bar-Haim, Idan Szpektor and Oren Glickman. 2005. Definition and Analysis of Intermediate Entailment Levels. In Proceedings of ACL 2005 Workshop on Empirical Modeling of Semantic Equivalence and Entailment. (pdf)

Idan Szpektor. 2005. Scaling Web-based Acquisition of Entailment Relations, M.Sc. thesis, Tel-Aviv University, Department of Computer Science. (doc)

Idan Szpektor, Hristo Tanev, Ido Dagan and Bonaventura Coppola. 2004. Scaling Web-based Acquisition of Entailment Relations. In Proceedings of EMNLP 2004. (pdf)

Scholarships

• 2008 - Wolf Foundation scholarship
• 2006 - President's scholarship of excellence

Academic Activities

Invited Talks and Seminars

• Tutorial on Textual Entailment. NAACL 2010. (web-site)
• Augmenting WordNet-based Inference with Argument Mapping. BISFAI 2009, Bar Ilan University, Israel. (web-site)
• Learning Entailment Rules for Unary Templates. Israeli Seminar on Computational Linguistics 2008, Bar Ilan University, Israel. (web-site)
• Entailment Rules: Learning and Inference. Columbia University; NYU. 2008.
• Learning Canonical Forms of Entailment Rules. Israeli Seminar on Computational Linguistics 2007, Bar Ilan University, Israel. (web-site)
• Textual Entailment: Framework, Learning and Applications. Microsoft Research; Yahoo Research; ISI; Stanford; Harvard; NYU. 2006. (video)
• Investigating a Generic Paraphrase-based Approach for Relation Extraction. Israeli Seminar on Computational Linguistics 2006, University of Haifa, Israel. (web-site)
• Scaling Web-based Acquisition of Entailment Relations. Israeli Seminar on Computational Linguistics 2004, Bar Ilan University, Israel. (web-site)

Others

• Co-supervisor of Roni Ben Aharon for his masters degree, Bar Ilan University 2009-2010.
• Program Committee member, Student Workshop at ACL 2010.
• Program Committee member, TextInfer 2009.
• Program Committee member, EMNLP 2009.
• Reviewer, ACL 2009.
• Program Committee member, NSF Symposium on Semantic Knowledge Discovery, Organization and Use, 2008.
• Co-organizer of the Israeli Seminar on Computational Linguistics (ISCOL) 2008
• Reviewer, ACL 2008
• Reviewer, COLING 2008
• Reviewer, EMNLP 2008
• Co-organizer, Second Recognising Textual Entailment (RTE) Challenge, 2006

Resources

TEASE is an algorithm for acquisition of entailment relations. Given a lexical-syntactic input template, a parse sub-tree with variable slots, the algorithm automatically learns other templates that are candidates for entailment relation with the input template. The direction of the entailment relation is not learned in this version, so the resulting relation can be either that the input entails the candidate, the candidate entails the input or both entail each other (paraphrases). The structure of the candidates is also learned as part of the acquisition.

The current knowledge collection available consists of 136 different templates that were given as input. Under each directory you can find two files: pivot.xml, containing the description of the input template, and learned_templates.xml, containing the description of all the learned templates for that input template. All the templates in this collection are learned from the Web.

The current TEASE knowledge collection is available for research purposes: TEASE collection.

Please refer to the following publication when using this resource:

Idan Szpektor, Hristo Tanev, Ido Dagan and Bonaventura Coppola. 2004. Scaling Web-based Acquisition of Entailment Relations. in Proceedings of EMNLP 2004

Courses

Introduction to Communication Networks - Fall semester 2006-2007

Introduction to Communication Networks - Fall semester 2005-2006