Eva Maria Vecchi's Homepage


Welcome to my homepage! I am currently a Research Associate in the Natural Language and Information Processing (NLIP) research
group of the University of Cambridge, working on the DisCoTex Project.

Research Interests

Distributional Semantics; Formal Semantics; Compositionality; Meaning Representation; Corpus-based Natural Language Processing; Acquisition of Semantic Knowledge


Ph.D. in Cognitive and Brain Sciences. Center for Brain and Mind Sciences (CIMeC), Università di Trento, Rovereto (TN) Italy. December 2013.

  • Advisors: Roberto Zamparelli and Marco Baroni
  • Topic of Dissertation: Compositional Distributional Semantics
  • Center for Language, Interaction and Computation (CLIC) Laboratory

M.Sc. in Linguistics. Georgetown University, Washington DC, USA. May 2007.

  • Advisor: Markus Dickinson
  • Thesis: Personal Names: Recognition of variants incorporating the understanding of possible variations

B.A. in Linguistics. University of Colorado at Boulder, Boulder, CO, USA. May 2005.

  • Minors in Mathematics and Italian

Back to the index


E.M. Vecchi, M. Marelli, R. Zamparelli and M. Baroni. Spicy adjectives and nominal donkeys: Capturing semantic deviance using compositionality in distributional spaces. (In Review)

L. Fǎgǎrǎşan, E.M. Vecchi and S. Clark. 2014. From distributional semantics to feature norms: Grounding semantic models in human perceptual data. NIPS Learning Semantics Workshop 2014. Montreal, Canada. [pdf]

E.M. Vecchi, R. Zamparelli and M. Baroni. 2013. Studying the recursive behaviour of adjectival modification with compositional distributional semantics. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing (pp. 141-151). Seattle, WA. [pdf] [bib]

A. Lazaridou, E.M. Vecchi and M. Baroni. 2013. Fish transporters and miracle homes: How compositional distributional semantics can help NP parsing. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing (pp. 1908-1913). Seattle, WA. [pdf] [bib] [datasets]

E.M. Vecchi, R. Zamparelli, and M. Baroni. 2013. Compositionnaliteé en sémantique distributionnelle et ordonnancement des adjectifs. In Actes de MIXEUR 2013: Méthodes mixtes pour l'analyse syntaxique et sémantique du français, pages 99-102, Les Sables d'Olonne, France. [pdf] [bib]

G. Boleda, E.M. Vecchi, M. Cornudella and L. McNally. 2012. First-order vs. higher-order modification in distributional semantics. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing (pp. 1223-1233). Jeju Island, Korea. [pdf] [bib] [datasets]

E.M. Vecchi, M. Baroni and R. Zamparelli. 2011. (Linear) maps of the impossible: Capturing semantic anomalies in distributional space. In Proceedings of the ACL DISCo (Distributional Semantics and Compositionality) Workshop (pp. 1-9). Portland, Oregon. [pdf] [bib] [datasets]

A. Lenci, S. Montemagni, E.M. Vecchi, G. Venturi. 2011. Enriching the ISST-TANL Corpus with Semantic Frames. EVALITA 2011.

G. Attardi, S. Dei Rossi, F. Dell'Orletta, E.M. Vecchi. 2009. The Tanl Named Entity Recognizer at Evalita 2009. In Proceedings of the 2nd Special Issue on Evaluation of NLP and Speech Tools for Italian (EVALITA 2009). Reggio Emilia, Italy. December 2009. [pdf] [bib]

G. Attardi, A. Fuschetto, F. Tamberi, M. Simi, E.M. Vecchi. 2009. Experiments in tagger combination: arbitrating, guessing, correcting, suggesting. In Proceedings of the 2nd Special Issue on Evaluation of NLP and Speech Tools for Italian (EVALITA 2009). Reggio Emilia, Italy. December 2009. [pdf] [bib]

G. Venturi, A. Lenci, S. Montemagni, E.M. Vecchi, M.T. Sagri, D. Tiscornia, T. Agnoloni. 2009. Towards a FrameNet Resource for the Legal Domain. In the 3rd Workshop on Legal Ontologies and Artificial Intelligence Techniques joint with 2nd Workshop on Semantic Processing of Legal Text. (LOAIT 2009). Barcelona, Spain. 8 June 2009. [pdf] [bib]

K. Miller, M. Arehart, C. Ball, J. Polk, A. Rubenstein, K. Samuel, E. Schroeder, E.M. Vecchi, C. Wolf. 2008. An Infrastructure, Tools and Methodology for Evaluation of Multicultural Name Matching Systems. In Proceedings of the Sixth International Language Resources and Evaluation (LREC'08). Marrakech, Morocco. 28-30 May 2008. [pdf] [bib]

Back to the index


  • By-Fellow at Churchill College
  • IWCS 2015 Program Committee Member (link)
  • SSST-2014 Workshop Co-Organizer (link)
  • *SEM 2014 Program Committee Member (link)
  • COLING-2014 Program Committee Member (link)
  • ACL-2014 SRW Program Committee Member (link)
  • ACL-2013 Student Research Workshop Co-Chair (link)
  • *SEM 2013 Program Committee Member (link)
  • IWCS-2013 Workshop Program Committee Member: Towards a Formal Distributional Semantics (link)

Resources and Tools


Resources and Public Code

COMPOSES Github Repository: All the code and resources to be developed by COMPOSES will be publically and freely released.

EMNLP 2012 Datasets: The intersective, subsective, and intensional AN datasets used in the EMNLP 2012 experiments are available here: data-emnlp2012.zip

DISCo 2011 Datasets: The evaluation sets of unattested ANs manually annotated as either semantically deviant or acceptable for the 25 test adjectives are available here.

Back to the index


Email: Eva DOT Vecchi AT cl.cam.ac.uk

Snail Mail: Eva Maria Vecchi, Computer Laboratory, University of Cambridge, 15 JJ Thomson Avenue, Cambridge CB3 0FD, United Kingdom.

Phone: (+44) (0)1223 763765

Back to the index