Summary of the paper
| Title | Generating FrameNets of Various Granularities: The FrameNet Transformer |
|---|---|
| Authors | Josef Ruppenhofer, Jonas Sunde and Manfred Pinkal |
| Abstract | We present a method and a software tool, the FrameNet Transformer, for derivingcustomized versions of the FrameNet database based on frame and frame elementrelations. The FrameNet Transformer allows users to iteratively coarsen theFrameNet sense inventory in two ways. First, the tool can merge entire framesthat are related by user-specified relations. Second, it can merge word sensesthat belong to frames related by specified relations. Both methods can beinterleaved. The Transformer automatically outputs format-compliant FrameNetversions, including modified corpus annotation files that can be used forautomatic processing. The customized FrameNet versions can be used to determinewhich granularity is suitable for particular applications. In our evaluation ofthe tool, we show that our method increases accuracy of statistical semanticparsers by reducing the number of word-senses (frames) per lemma, andincreasing the number of annotated sentences per lexical unit and frame. Wefurther show in an experiment on the FATE corpus that by coarsening FrameNet wedo not incur a significant loss of information that is relevant to theRecognizing Textual Entailment task. |
| Language | Textual Entailment and Paraphrasing |
| Topics | Lexicon, lexical database, Corpus (creation, annotation, etc.), Textual Entailment and Paraphrasing |
Full paper  |
Generating FrameNets of Various Granularities: The FrameNet Transformer |
| Bibtex | @InProceedings{RUPPENHOFER10.552, author = {Josef Ruppenhofer, Jonas Sunde and Manfred Pinkal}, title = {Generating FrameNets of Various Granularities: The FrameNet Transformer}, 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} } |