Marta Recasens
Research Scientist, Google Inc.
recasens <locative preposition> google <small round mark> com
1600 Amphitheatre Pkwy
Mountain View, CA 94043
USA
|
Publications | Invited Talks | Committees | Research Projects | Grants & Awards | Education | Languages | Technical Skills | Materials |
|
|
I came to the world with my eyes wide open, which was probably an early sign of an inquiring mind. My primary research focus is on corpus-based approaches to semantics and pragmatics. I am interested in interdisciplinary work between linguistics, computer science, cognition, statistics... The problem that has kept me busy since I entered the field of Natural Language Processing (NLP) is coreference resolution, which is still today one of the most challenging problems in NLP. Since 2013 I am a Research Scientist at Google. Prior to that, I was a a Postdoctoral Fellow at Stanford University's Linguistics Department, and a member of the Stanford NLP Group. I worked with Prof. Dan Jurafsky. I completed my PhD on coreference resolution in 2010 at the University of Barcelona, where I was a member of the CLiC research group. The title of my thesis was Coreference: Theory, Annotation, Resolution and Evaluation. My advisors were Prof. M. Antònia Martí (UB) and Prof. Eduard Hovy (USC). |
|
Publications
2017
Ingrid L. Falkum, Marta Recasens, and Eve Clark. 2017. "The moustache sits down first": on the acquisition of metonymy. Journal of Child Language, 44(1):87-119. Available on CJO 2016 DOI:10.1017/S0305000915000720.
2016
Marta Recasens and Sameer Pradhan. 2016. Evaluation Campaigns. In M. Poesio, R. Stuckardt and Y. Versley (eds.), Anaphora Resolution: Algorithms, Resources, and Applications, pages 165-208. Springer-Verlag Berlin Heidelberg.
Massimo Poesio, Sameer Pradhan, Marta Recasens, Kepa Rodríguez, and Yannick Versley. 2016. Annotated Corpora and Annotation Tools. In M. Poesio, R. Stuckardt and Y. Versley (eds.), Anaphora Resolution: Algorithms, Resources, and Applications, pages 97-140. Springer-Verlag Berlin Heidelberg.
Marta Recasens, Zhichao Hu, and Olivia Rhinehart. 2016. Sense Anaphoric Pronouns: Am I One?. In Proceedings of CORBON 2016, pages 1-6.
2015
Sujay Kumar Jauhar, Raul Guerra, Edgar Gonzàlez, and Marta Recasens. 2015. Resolving Discourse-Deictic Pronouns: A Two-Stage Approach to Do It. In Proceedings of *SEM 2015, pages 299-308.
Marie-Catherine de Marneffe, Marta Recasens, and Christopher Potts. 2015. Modeling the Lifespan of Discourse Entities with Application to Coreference Resolution. Journal of Artificial Intelligence Research, 52(2015):445-475.
2014
Sameer Pradhan, Xiaoqiang Luo, Marta Recasens, Eduard Hovy, Vincent Ng, and Michael Strube. 2014. Scoring Coreference Partitions of Predicted Mentions: A Reference Implementation. In Proceedings of ACL 2014, pages 30-35.
Xiaoqiang Luo, Sameer Pradhan, Marta Recasens, and Eduard Hovy. 2014. An Extension of BLANC to System Mentions. In Proceedings of ACL 2014, pages 24-29.
Marta Recasens, Liliana Tolchinsky, and M. Antònia Martí. 2014. Coreference is not always either/or: Psycholinguistic evidence for near-identity. Language, Cognition and Neuroscience, 29(7):844-855.
2013
Marta Recasens, Cristian Danescu-Niculescu-Mizil, and Dan Jurafsky. 2013. Linguistic Models for Analyzing and Detecting Biased Language. In Proceedings of ACL 2013, pages 1650-1659.
Marta Recasens, Marie-Catherine de Marneffe, and Christopher Potts. 2013. The Life and Death of Discourse Entities: Identifying Singleton Mentions. In Proceedings of NAACL-HLT 2013, pages 627-633. [video] Best Short Paper Award
Marta Recasens, Matthew Can, and Dan Jurafsky. 2013. Same Referent, Different Words: Unsupervised Mining of Opaque Coreferent Mentions. In Proceedings of NAACL-HLT 2013, pages 897-906. [data] [video]
2012
Heeyoung Lee, Marta Recasens, Angel Chang, Mihai Surdeanu, and Dan Jurafsky. 2012. Joint Entity and Event Coreference Resolution across Documents. In Proceedings of EMNLP 2012, pages 489-500.
David McClosky, Wanxiang Che, Marta Recasens, Mengqiu Wang, Richard Socher, and Christopher D. Manning. 2012. Stanford's System for Parsing the English Web. In Notes of the First Workshop on Syntactic Analysis of Non-Canonical Language (SANCL 2012).
Marta Recasens, M. Antònia Martí, and Constantin Orasan. 2012. Annotating Near-Identity from Coreference Disagreements. In Proceedings of LREC 2012, pages 165-172.
M. Antònia Martí, Raquel G. Alhama, and Marta Recasens. 2012. Los avances tecnológicos y la ciencia del lenguaje. In T. Jiménez Juliá, B. López Meirama, V. Vázquez Rozas, and Alexandre Veiga (eds.), Cum corde et in nova grammatica. Estudios ofrecidos a Guillermo Rojo. Santiago de Compostela: Universidade de Santiago de Compostela Publicaciones, pages 543-553.
Lluís Màrquez, Marta Recasens, and Emili Sapena. 2012. Coreference Resolution: An Empirical Study Based on SemEval-2010 Shared Task 1. Language Resources and Evaluation, 47(3):661-694.
2011
Marta Recasens, Eduard Hovy, and M. Antònia Martí. 2011. Identity, non-identity, and near-identity: Addressing the complexity of coreference. Lingua, 121(6):1138-1152. Best PhD Paper Award by the University of Barcelona
Marta Recasens and Eduard Hovy. 2011. BLANC: Implementing the Rand Index for coreference evaluation. Natural Language Engineering, 17(4):485-510. © Cambridge University Press 2010
2010
Marta Recasens and Marta Vila. 2010. On Paraphrase and Coreference. Computational Linguistics, 36(4):639-647.
Marta Recasens and Eduard Hovy. 2010. Coreference Resolution across Corpora: Languages, Coding Schemes, and Preprocessing Information. In Proceedings of ACL 2010, pages 1423-1432.
Marta Recasens, Lluís Màrquez, Emili Sapena, M. Antònia Martí, Mariona Taulé, Véronique Hoste, Massimo Poesio, and Yannick Versley. 2010. SemEval-2010 Task 1: Coreference Resolution in Multiple Languages. In Proceedings of the ACL International Workshop on Semantic Evaluation (SemEval-2010), pages 1-8.
Marta Recasens, Eduard Hovy, and M. Antònia Martí. 2010. A Typology of Near-Identity Relations for Coreference (NIDENT). In Proceedings of LREC 2010, pages 149-156.
Marta Recasens and M. Antònia Martí. 2010. AnCora-CO: Coreferentially annotated corpora for Spanish and Catalan. Language Resources and Evaluation, 44(4):315-345.
2009
Marta Recasens and Eduard Hovy. 2009. A Deeper Look into Features for Coreference Resolution. In S. Lalitha Devi, A. Branco, and R. Mitkov (eds.), Anaphora Processing and Applications (DAARC 2009), LNAI 5847:29-42. Springer-Verlag Berlin Heidelberg.
Marta Recasens. 2009. A Chain-starting Classifier of Definite NPs in Spanish. In Proceedings of the EACL Student Research Workshop, pages 46-53.
Marta Recasens, M. Antònia Martí, and Mariona Taulé. 2009. First-mention Definites: More than Exceptional Cases. In S. Featherston and S. Winkler (eds.), The Fruits of Empirical Linguistics. Volume 2: Product, pages 217-237. Berlin: de Gruyter.
Marta Recasens, M. Antònia Martí, Mariona Taulé, Lluís Màrquez, and Emili Sapena. 2009. SemEval-2010 Task 1: Coreference Resolution in Multiple Languages. In Proceedings of the NAACL HLT Workshop on Semantic Evaluations: Recent Achievements and Future Directions (SEW 2009), pages 70-75.
2008
Manuel Bertran, Oriol Borrega, Marta Recasens, and Bàrbara Soriano. 2008. AnCoraPipe: A tool for multilevel annotation. Procesamiento del Lenguaje Natural, 41:291-292.
Marta Recasens. 2008. Discourse Deixis and Coreference: Evidence from AnCora. In Proceedings of the 2nd Workshop on Anaphora Resolution (WAR II). NEALT Proceedings Series Vol. 2:73-82.
Mariona Taulé, M. Antònia Martí, and Marta Recasens. 2008. AnCora: Multilevel Annotated Corpora for Catalan and Spanish. In Proceedings of LREC 2008, pages 96-101.
2007
Marta Recasens, M. Antònia Martí, and Mariona Taulé. 2007. Where Anaphora and Coreference Meet. Annotation in the Spanish CESS-ECE Corpus. In Proceedings of RANLP 2007, pages 504-509.
Marta Recasens, M. Antònia Martí, and Mariona Taulé. 2007. Text as Scene: Discourse Deixis and Bridging Relations. Procesamiento del Lenguaje Natural, 39:205-212.
Invited Talks
• "The Long Tail of Coreference Resolution"
University of California at Santa Cruz, California. April 2015.
• "What Real Data Reveals About Coreference"
University of California at Davis, California. April 2014.
• "Taking Coreference Resolution beyond the 60% Performance Barrier"
Carnegie Mellon University, Pittsburgh, Pennsylvania. April 2013.
• "Deconstructing Coreference"
University of the Basque Country, San Sebastián, Spain. June 2011.
University of Wolverhampton, Wolverhampton, UK. April 2011.
Universitat Pompeu Fabra, Barcelona, Spain. April 2011.
Universitat Politècnica de Catalunya, Barcelona, Spain. November 2010.
• "Learning-based Coreference Resolution for Spanish and Catalan"
Information Sciences Institute, University of Southern California, Marina del Rey, California. May 2009.
Committees
• Chair of ACL 2015 (Area of Discourse, Coreference and Pragmatics), EACL 2012 - Student Research Workshop.
• Member of the Program Committee of ACL 2014, 2n Workshop on EVENTS, EMNLP 2014, ACL 2013, 1st Workshop on EVENTS, *SEM 2013, NAACL 2013 - Student Research Workshop, COLING 2012, CoNLL-2012 Shared Task, EACL 2012, CREDISLAS Workshop, IJCNLP 2011, Language Resources and Evaluation Special issue on Computational Semantic Analysis of Language: SemEval-2010, RANLP 2011 - Student Research Workshop, RANLP 2011, DAARC 2011, Beyond Semantics 2011, LAW IV, CBA 2010, DAARC 2009, CBA 2008.
• Reviewer of TACL, Revue TAL, ACL 2011, SEPLN 2010, LREC 2010, RANLP 2009.
• Member of the Organizing Committee of Task1: Coreference Resolution in Multiple Languages at SemEval-2(2010).
• Member of the Organizing Committee of CBA 2008.
• Member of the EACL Student Board (2009-2011).
Research Projects
Title: Coreference as a continuum: Crosslinguistic validation and computational framework (2010 PBR 00039)
Funded by: Government of Catalonia.
Duration: 2011.
Participants: University of Barcelona, University of Wolverhampton.
PI: M. Antònia Martí.
Title: TEXT-Knowledge 2.0: Knowledge modeling before the new challenges of digital communication (TIN2009-13391-C04-04). Subproject of TEXT-MESS 2.0
Funded by: Spanish Ministry of Science and Innovation.
Duration: 2010-2012.
Participants: University of Alicante, Technical University of Valencia, University of Barcelona, University of Jaén.
PI: M. Antònia Martí.
Title: ANCORA-NET: Multilingual integration of semantic resources (FFI2009-06497-E/FILO)
Funded by: Spanish Ministry of Science and Innovation.
Duration: 2010.
Participants: University of Barcelona.
PI: Mariona Taulé.
Title: ANCORA-NOM: Semantic annotation of NPs in the AnCora corpora (FFI2008-02691-E/FILO)
Funded by: Spanish Ministry of Science and Innovation.
Duration: 2009.
Participants: University of Barcelona.
PI: Mariona Taulé.
Title: Praxem, semantic and pragmatic annotation of the CESS-ECE corpus (HUM2006-27378-E)
Funded by: Spanish Ministry of Education and Science.
Duration: 2007-2008.
Participants: University of Barcelona, Technical University of Catalonia, University of the Basque Country, University of Alicante.
PI: Mariona Taulé.
Title: Lang2World: Discovering the world knowledge codified in the language (TIN2006-15265-C06-06). Subproject of TEXT-MESS.
Funded by: Spanish Ministry of Education and Science.
Duration: 2006-2009.
Participants: University of Alicante, Technical University of Valencia, University of Barcelona, Technical University of Catalonia, University of Jaén, National Open University of Spain (UNED).
PI: M. Antònia Martí.
Title: CESS-ECE: Corpus Syntactically and Semantically Annotated of Spanish, Catalan and Basque (HUM2004-21127-E)
Funded by: Spanish Ministry of Education and Science.
Duration: 2005-2007.
Participants: University of Barcelona, Technical University of Catalonia, University of the Basque Country.
PI: M. Antònia Martí.
Grants & Awards
2013 • NAACL Best Short Paper.
2011 - 2013 • Postdoctoral Fellowship ("Beatriu de Pinós") by Generalitat de Catalunya.
2011 • "J. Manuel Blecua" Award to the best paper resulting from a PhD Thesis. University of Barcelona.
2009 • Best Paper Award at the 4th ISI Graduate Student Symposium. Information Sciences Institute, University of Southern California.
2009 • Study abroad fellowship in the US by the Spanish Ministry of Education.
2007 - 2010 • Doctoral Fellowship by the Spanish Ministry of Education and Science.
2007 • Special Mention, B.A. National Awards of Spain.
2007 • University of Barcelona's B.A. Extraordinary Award.
Education
2011-2013 • Postdoc, Stanford University.
2010 • Ph.D., Linguistics, University of Barcelona.
Recasens, M. (2010) Coreference: Theory, Annotation, Resolution and Evaluation. PhD Thesis. University of Barcelona.
2009 • Research stay at the Information Sciences Institute, University of Southern California.
2008 • M.A., Linguistics, University of Barcelona.
Recasens, M. (2008) Towards Coreference Resolution for Catalan and Spanish. Master Thesis. University of Barcelona.
2006 • B.A., English Philology, University of Barcelona.
Languages
Catalan Mother tongue
Spanish Second mother tongue
English Fluent
German Fluent
French Good
Hungarian Basic
Technical Skills
• Programming Languages: Java, C++, R
• Markup Languages: LaTeX, XML, Wikitext
Materials
Stimuli used in the psycholinguistic experiment about near-identity [pdf]
Coreference dictionary [zip]