Marta Vila Rigat

Passion for language has always accompanied me. As a child, before learning to write, I can clearly remember imitating the adult world around me by taking a sheet of paper and pencil and drawing lines, lines that wanted to be those of writing.

Naturally it was that I followed this instinct later on in life by studying Hispanic Philology at the University of Barcelona. I also obtained a Master's degree in Expert in Spanish as a Second Language in Professional Environments at the same university.

I recently completed my PhD in Cognitive Science and Language in the Department of Linguistics at the University of Barcelona. My PhD thesis, supervised by Dr. M. Antònia Martí (UB) and Dr. Horacio Rodríguez (UPC), analyzes paraphrasing in the framework of computational linguistics. It specifically focuses in the characterization of paraphrasing and in the creation and annotation of paraphrase corpora that can be the basis both for research and for future resources and applications. The knowledge and resources created as a result of this work have been applied to automatic plagiarism detection in order to empirically analyze their potential.

During the course of my PhD, I also carried out a research stay in the Department of Computing at Macquarie University, in Sydney, under the supervision of Dr. Mark Dras. This experience opened the doors for me to new perspectives on paraphrasing, to new ways of working and also to new ways of living and understanding the world.

Publications

PhD Thesis

Vila, Marta. 2013. Paraphrase Scope and Typology. A Data-Driven Approach from Computational Linguistics. PhD thesis. Universitat de Barcelona, Barcelona.

Journal Publications 

Vila, Marta;  Bertran, Manuel;  M. Antònia Martí; and Horacio Rodríguez. 2015. Corpus annotation with paraphrase types: new annotation scheme and inter-annotator agreement measures. Language Resources and Evaluation, 49(1):77-105.

Vila, Marta; Horacio Rodríguez; and M. Antònia Martí. 2015. Relational paraphrase acquisition from Wikipedia: The WRPA method and corpus. Natural Language Engineering, 21(3):355-389. Copyright © Cambridge University Press 2013.

Vila, Marta; M. Antònia Martí; and Horacio Rodríguez. 2014. Is this a paraphrase? What kind? Paraphrase boundaries and typology. Open Journal of Modern Linguistics, 4:205-218.

Barrón-Cedeño, Alberto; Marta Vila; M. Antònia Martí; and Paolo Rosso. 2013. Plagiarism meets paraphrasing: Insights for the next generation in automatic plagiarism detection. Computational Linguistics, 39(4):917-947.

Vila, Marta; and Mark Dras. 2012. Tree edit distance as a baseline approach for paraphrase representation. Procesamiento del Lenguaje Natural, 48:89-95.

Vila, Marta; M. Antònia Martí; and Horacio Rodríguez. 2011. Paraphrase concept and typology. A linguistically based and computationally oriented approach. Procesamiento del Lenguaje Natural, 46:83-90. 

Recasens, Marta; and Marta Vila. 2010. On paraphrase and coreference. Computational Linguistics, 36(4):639-647. 

Vila, Marta; Horacio Rodríguez; and M. Antònia Martí. 2010. WRPA: A system for relational paraphrase acquisition from Wikipedia. Procesamiento del Lenguaje Natural, 45:11-19.

Vila, Marta; Santiago González; M. Antònia Martí; Joaquim Llisterri; and M. Jesús Machuca. 2010. ClInt: A bilingual Spanish-Catalan spoken corpus of clinical interviews. In Procesamiento del Lenguaje Natural, 45:105-111.   

España-Bonet, Cristina; Marta Vila; Horacio Rodríguez; and M. Antònia Martí. 2009. CoCo, a web interface for corpora compilation. Procesamiento del Lenguaje Natural, 43:367-368.

Conference Publications

Gonzàlez, Edgar; Horacio Rodríguez; Jordi Turmo; Pere R. Comas; Ali Naderi; Alicia Ageno; Emili Sapena; Marta Vila; and M. Antònia Martí. 2012. The TALP participation at TAC-KBP 2012. In Proceedings of the Fifth Text Analysis Conference (TAC 2012), Gaithersburg.

Chapters in Books 

Barrón-Cedeño, Alberto; Marta Vila; and Paolo Rosso. 2012. Detección automática de plagio: De la copia exacta a la paráfrasis. In Elena Garayzábal, Miriam Jiménez and Mercedes Reigosa (Eds.). Lingüística Forense: La Lingüística en el Ámbito Legal y Policial. Madrid, Euphonía Ediciones, pages 71-101.

Resources and Tools

CoCo interface

Paraphrase corpora