A Knowledge Based Approach for Capturing Rich Semantic Representations from Text

In this paper, we present a knowledge based approach to capture semantic representations from natural language for a class of applications where the representations of interest are known in advance. Our approach performs this task by generating phrases from these representations and matching these phrases against text using a set of syntactic and semantic transformations. The representation that best matches a piece of text is selected as its meaning. We evaluate our approach on a corpus of news articles collected from over 150 online news sources, and show how our approach performs well on capturing semantic representations from text.

[1]  Rada Mihalcea,et al.  PageRank on Semantic Networks, with Application to Word Sense Disambiguation , 2004, COLING.

[2]  Peter Z. Yeh,et al.  Semantic Interpretation of the Web without the Semantic Web: Toward Business-Aware Web Processors , 2007 .

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

[4]  John B. Lowe,et al.  The Berkeley FrameNet Project , 1998, ACL.

[5]  C. Fillmore.  Some Problems for Case Grammar , 1971 .

[6]  Stan Szpakowicz,et al.  Semiautomatic recognition of semantic relationships in english technical texts , 1998 .

[7]  Peter Clark,et al.  A library of generic concepts for composing knowledge bases , 2001, K-CAP '01.

[8]  Peter Clark,et al.  Acquiring and Using World Knowledge Using a Restricted Subset of English , 2005, FLAIRS Conference.

[9]  Daniel Jurafsky,et al.  Automatic Labeling of Semantic Roles , 2002, CL.

[10]  John F. Sowa,et al.  Conceptual Structures: Information Processing in Mind and Machine , 1983 .

[11]  Stan Szpakowicz,et al.  Semi-Automatic Recognition of Noun Modifier Relationships , 1998, ACL.

[12]  Jerry R. Hobbs,et al.  Learning by Reading: A Prototype System, Performance Baseline and Lessons Learned , 2007, AAAI.

[13]  M. F. Porter,et al.  An algorithm for suffix stripping , 1997 .

[14]  Alex Kass,et al.  Using Lightweight NLP and Semantic Modeling to Realize the Internet's Potential as a Corporate Radar , 2006, AAAI Fall Symposium: Capturing and Using Patterns for Evidence Detection.

[15]  Kadri Hacioglu,et al.  Semantic Role Labeling Using Dependency Trees , 2004, COLING.

[16]  Dan Roth,et al.  Modeling Discriminative Global Inference , 2007 .

[17]  Ted Pedersen,et al.  Using Measures of Semantic Relatedness for Word Sense Disambiguation , 2003, CICLing.

[18]  Daniel Jurafsky,et al.  Semantic Role Labeling Using Different Syntactic Views , 2005, ACL.

[19]  Peter Z. Yeh,et al.  A Unified Knowledge Based Approach for Sense Disambiguation and Semantic Role Labeling , 2006, AAAI.

[20]  Philippe Langlais,et al.  Evaluating Variants of the Lesk Approach for Disambiguating Words , 2004, LREC.