ABOUT MY WORK
My research area is applied semantic processing, mostly based on data driven machine learning methods. My group, together with colleagues established the textual entailment recognition paradigm.
We are investigating various aspects of natural language inference, including detecting the semantics structure of sentences and identifying the sematnive relationships between words and phrases.
More recently, we have been focusing on the challenge of extracting and representing the consolidated information expressed in multiple texts and in developing novel interactive summarization approaches, which allow people to explore such information.
Omer Levy, Ido Dagan, Gabriel Stanovsky, Judith Eckle-Kohler, Iryna Gurevych. Modeling Extractive Sentence Intersection via Subtree Entailment. Proceedings of The 26th International Conference on Computational Linguistics (COLING) | Osaka, Japan, 2016.
Gabriel Stanovsky, Judith Eckle-Kohler, Yevgeniy Puzikov, Ido Dagan, Iryna Gurevych. Integrating Deep Linguistic Features in Factuality Prediction over Unified Datasets. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL) | Vancouver, Canada, 2017.
Vered Shwartz, Gabriel Stanovsky, Ido Dagan. Acquiring Predicate Paraphrases from News Tweets. Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (* SEM) | 2017.
Rachel Wities, Vered Shwartz, Gabriel Stanovsky, Meni Adler, Ori Shapira, Shyam Upadhyay, Dan Roth, Eugenio Martinez Camara, Iryna Gurevych, Ido Dagan. A Consolidated Open Knowledge Representation for Multiple Texts. Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics (LSDSem), at EACL | Valencia, Spain, 2017.
Ori Shapira, Hadar Ronen, Meni Adler, Yael Amsterdamer, Judit Bar-Ilan, Ido Dagan. Interactive Abstractive Summarization for Event News Tweets. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP) | Copenhagen, Denmark, 2017.
Learning lexical semantic relations between lexical elements.
Extracting propositions from text.
An open information representation scheme for textual information in multiple texts.
Interactive summarization for text exploration.
Identifying cross-document coreference.