Summary of the paper

Title FrameNet Translation Using Bilingual Dictionaries with Evaluation on the English-French Pair
Authors Claire Mouton, Gaël de Chalendar and Benoît Richert
Abstract Semantic Role Labeling cannot be performed without an associated linguisticresource. A key resource for such a task isthe FrameNet resource based on Fillmore’s theory of frame semantics. Likemany linguistic resources, FrameNet has beenbuilt by English native speakers for the English language. To overcome the lackof such resources in other languages, wepropose a new approach to FrameNet translation by using bilingual dictionariesand filtering the wrong translations. Wedefine six scores to filter, based on translation redundancy and FrameNetstructure. We also present our work on theenrichment of the obtained resource with nouns. This enrichment uses semanticspaces built on syntactical dependenciesand a multi-represented k-NN classifier. We evaluate both the tasks on theFrench language over a subset of ten framesand show improved results compared to the existing French FrameNet. Our finalresource contains 15,132 associationslexical units-frames for an estimated precision of 86%.
Language Semantics
Topics Acquisition, Lexicon, lexical database, Semantics
Full paper FrameNet Translation Using Bilingual Dictionaries with Evaluation on the English-French Pair
Bibtex @InProceedings{MOUTON10.485,
  author = {Claire Mouton, Gaël de Chalendar and Benoît Richert},
  title = {FrameNet Translation Using Bilingual Dictionaries with Evaluation on the English-French Pair},
  booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)},
  year = {2010},
  month = {may},
  date = {19-21},
  address = {Valletta, Malta},
  editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias},
  publisher = {European Language Resources Association (ELRA)},
  isbn = {2-9517408-6-7},
  language = {english}
 }
Powered by ELDA © 2010 ELDA/ELRA