Summary of the paper
| Title | Pattern-Based Extraction of Negative Polarity Items from Dependency-Parsed Text |
|---|---|
| Authors | Fabienne Fritzinger, Frank Richter and Marion Weller |
| Abstract | We describe a new method for extracting Negative Polarity Item candidates (NPIcandidates) from dependency-parsed German text corpora. Semi-automaticextraction of NPIs is a challenging task since NPIs do not have uniformcategorical or other syntactic properties that could be used for detectingthem; they occur as single words or as multi-word expressions of almost anysyntactic category. Their defining property is of a semantic nature, they mayonly occur in the scope of negation and related semantic operators. In contrastto an earlier approach to NPI extraction from corpora, we specifically targetmulti-word expressions. Besides applying statistical methods to measure theco-occurrence of our candidate expressions with negative contexts, we alsoapply linguistic criteria in an attempt to determine to which degree they areidiomatic. Our method is evaluated by comparing the set of NPIs we found withthe most comprehensive electronic list of German NPIs, which currently contains165 entries. Our method retrieved 142 NPIs, 114 of which are new. |
| Language | Semantics |
| Topics | MultiWord Expressions & Collocations, Lexicon, lexical database, Semantics |
Full paper  |
Pattern-Based Extraction of Negative Polarity Items from Dependency-Parsed Text |
| Bibtex | @InProceedings{FRITZINGER10.267, author = {Fabienne Fritzinger, Frank Richter and Marion Weller}, title = {Pattern-Based Extraction of Negative Polarity Items from Dependency-Parsed Text}, 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} } |