Using Semantic Features Derived from Word-Space Models for Swedish Coreference Resolution

We investigate the effect of using wordspace models as an approximation of the kind of lexico-semantic and commonsense knowledge needed for coreference resolution of definite descriptions, that is, definite NPs with a common noun as head, for Swedish news text. We contrast a system using semantic knowledge from the word-space models with a semantically ignorant system and another system drawing its semantic information from a semantic dictionary called SynLex. We demonstrate an improvement in the results for two different evaluation tasks for the system using word space-derived semantic information over both other systems.

[1]  Magnus Sahlgren,et al.  The Word-Space Model: using distributional analysis to represent syntagmatic and paradigmatic relations between words in high-dimensional vector spaces , 2006 .

[2]  Viggo Kann,et al.  Free construction of a free Swedish dictionary of synonyms , 2005, NODALIDA.

[3]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[4]  Piek Vossen.  Introduction to EuroWordNet , 1998 .

[5]  Michael Strube,et al.  The Influence of Minimum Edit Distance on Reference Resolution , 2002, EMNLP.

[6]  Hinrich Schütze,et al.  Automatic Word Sense Discrimination , 1998, Comput. Linguistics.

[7]  Renata Vieira,et al.  An Empirically-based System for Processing Definite Descriptions , 2000, CL.

[8]  Geoffrey Sampson,et al.  The Oxford Handbook of Computational Linguistics , 2003, Lit. Linguistic Comput..

[9]  Martha Palmer,et al.  Using semantic relations to improve information retrieval , 2005 .

[10]  Chris Brew,et al.  Lexical Clustering and Definite Description Interpretation , 1998 .

[11]  Walter Daelemans,et al.  A Coreference Corpus and Resolution System for Dutch , 2008, LREC.

[12]  Gene H. Golub,et al.  Matrix computations , 1983 .

[13]  Vincent Ng,et al.  Semantic Class Induction and Coreference Resolution , 2007, ACL.

[14]  Hwee Tou Ng,et al.  A Machine Learning Approach to Coreference Resolution of Noun Phrases , 2001, CL.

[15]  Walter Daelemans,et al.  Semantic and Syntactic Features for Dutch Coreference Resolution , 2008, CICLing.

[16]  Gregory Grefenstette,et al.  Explorations in automatic thesaurus discovery , 1994 .

[17]  T. Landauer,et al.  Indexing by Latent Semantic Analysis , 1990 .

[18]  Johan Carlberger,et al.  Implementing an Efficient Part-Of-Speech Tagger , 1999, Softw. Pract. Exp..

[19]  A. Student,et al.  Japan and the United States , 1953 .

[20]  Walter Daelemans,et al.  Memory-Based Language Processing , 2009, Studies in natural language processing.

[21]  Åke Lindmark Kerstin Lindvall Ann Mellenius Ingmarie Viberg.  The Swedish WordNet project , 2002 .

[22]  Joakim Nivre,et al.  MaltParser: A Language-Independent System for Data-Driven Dependency Parsing , 2007, Natural Language Engineering.

[23]  T. Landauer,et al.  A Solution to Plato's Problem: The Latent Semantic Analysis Theory of Acquisition, Induction, and Representation of Knowledge. , 1997 .

[24]  Edith Bolling.  Anaphora Resolution , 2006 .