Summary of the paper
| Title | A General Purpose FrameNet-based Shallow Semantic Parser |
|---|---|
| Authors | Bonaventura Coppola and Alessandro Moschitti |
| Abstract | In this paper we present a new FrameNet-based Shallow Semantic Parser. ShallowSemantic Parsing has been a popular Natural Language Processing task since the2004 and 2005 CoNLL Shared Task editions on Semantic Role Labeling, which werebased on the PropBank lexical-semantic resource. Nonetheless, efforts inextending such task to the FrameNet setting have been constrained by practicalsoftware engineering issues. We hereby analyze these issues, identify desirablerequirements for a practical parsing framework, and show the results of oursoftware implementation. In particular, we attempt at meeting requirementsarising from both a) the need of a flexible environment supporting currentongoing research, and b) the willingness of providing an effective platformsupporting preliminary application prototypes in the field. After introducingthe task of FrameNet-based Shallow Semantic Parsing, we sketch the systemprocessing workflow and summarize a set of successful experimental results,directing the reader to previous published papers for extended experimentdescriptions and wider discussion of the achieved results. |
| Language | Parsing |
| Topics | Tools, systems, applications, Semantics, Parsing |
Full paper  |
A General Purpose FrameNet-based Shallow Semantic Parser |
| Bibtex | @InProceedings{COPPOLA10.893, author = {Bonaventura Coppola and Alessandro Moschitti}, title = {A General Purpose FrameNet-based Shallow Semantic Parser}, 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} } |