Identifying Semantic Relations in Context: Near-misses and Overlaps

This paper addresses the problem of semantic relation identification for a set of relations difficult to differentiate: near-misses and overlaps. Based on empirical observations on a fairly large dataset of such examples we provide an analysis and a taxonomy of such cases. Using this taxonomy we create various contingency sets of relations. These semantic categories are automatically identified by training and testing three state-of-the-art semantic classifiers employing various feature sets. The results show that in order to identify such near-misses and overlaps accurately, a semantic relation identification system needs to go beyond the ontological information of the two nouns and rely heavily on contextual and pragmatic knowledge.

[1]  Robert N. Oddy,et al.  Using cause-effect relations in text to improve information retrieval precision , 2001, Inf. Process. Manag..

[2]  Dan I. Moldovan,et al.  A Logic-Based Semantic Approach to Recognizing Textual Entailment , 2006, ACL.

[3]  Preslav Nakov,et al.  Using Verbs to Characterize Noun-Noun Relations , 2006, AIMSA.

[4]  Maria Lapata,et al.  The Disambiguation of Nominalizations , 2002, CL.

[5]  Sanda M. Harabagiu,et al.  Cogex: A semantically and contextually enriched logic prover for question answering , 2007, J. Appl. Log..

[6]  Judith N. Levi,et al.  The syntax and semantics of complex nominals , 1978 .

[7]  Alla Rozovskaya,et al.  UIUC: A Knowledge-rich Approach to Identifying Semantic Relations between Nominals , 2007, ACL 2007.

[8]  Marti A. Hearst.  Automatic Acquisition of Hyponyms from Large Text Corpora , 1992, COLING.

[9]  Roxana Gîrju,et al.  Automatic Detection of Causal Relations for Question Answering , 2003, ACL 2003.

[10]  Mark Lauer,et al.  Corpus Statistics Meet the Noun Compound: Some Empirical Results , 1995, ACL.

[11]  Marian Olteanu,et al.  Support Vector Machines Applied to the Classification of Semantic Relations in Nominalized Noun Phrases , 2004, HLT-NAACL 2004.

[12]  Dan I. Moldovan,et al.  On the semantics of noun compounds , 2005, Comput. Speech Lang..

[13]  Roxana Girju,et al.  Improving the Interpretation of Noun Phrases with Cross-linguistic Information , 2007, ACL.

[14]  Douglas Herrmann,et al.  A Taxonomy of Part-Whole Relations , 1987, Cogn. Sci..

[15]  Barbara Rosario,et al.  Classifying the Semantic Relations in Noun Compounds via a Domain-Specific Lexical Hierarchy , 2001, EMNLP.

[16]  Dan Moldovan,et al.  Models for the Semantic Classification of Noun Phrases , 2004, HLT-NAACL 2004.

[17]  Preslav Nakov,et al.  SemEval-2007 Task 04: Classification of Semantic Relations between Nominals , 2007, Fourth International Workshop on Semantic Evaluations (SemEval-2007).

[18]  Roger K. Moore.  Computer Speech and Language , 1986 .

[19]  Maria Lapata.  The Disambiguation of Nominalisations , 2002 .

[20]  Dan I. Moldovan,et al.  Automatic Discovery of Part-Whole Relations , 2006, CL.

[21]  Stan Szpakowicz,et al.  Augmenting WordNet's Structure Using LDOCE , 2003, CICLing.

[22]  R. Girju,et al.  A knowledge-rich approach to identifying semantic relations between nominals , 2010, Inf. Process. Manag..

[23]  Timothy Baldwin,et al.  Interpreting Semantic Relations in Noun Compounds via Verb Semantics , 2006, ACL.

[24]  Karl E. Zimmer,et al.  Some General Observations about Nominal Compounds. Working Papers on Language Universals, No. 5. , 1971 .

[25]  Patrick Pantel,et al.  Ontologizing Semantic Relations , 2006, ACL.

[26]  Alla Rozovskaya,et al.  Automatic Semantic Relation Extraction with Multiple Boundary Generation , 2008, AAAI.