Combining Word Patterns and Discourse Markers for Paradigmatic Relation Classification

Distinguishing between paradigmatic relations such as synonymy, antonymy and hypernymy is an important prerequisite in a range of NLP applications. In this paper, we explore discourse relations as an alternative set of features to lexico-syntactic patterns. We demonstrate that statistics over discourse relations, collected via explicit discourse markers as proxies, can be utilized as salient indicators for paradigmatic relations in multiple languages, outperforming patterns in terms of recall and F1-score. In addition, we observe that markers and patterns provide complementary information, leading to significant classification improvements when applied in combination.

[1]  Sabine Schulte im Walde,et al.  Pattern-Based Distinction of Paradigmatic Relations for German Nouns, Verbs, Adjectives , 2013, GSCL.

[2]  Livio Robaldo,et al.  The Penn Discourse TreeBank 2.0. , 2008, LREC.

[3]  Ani Nenkova,et al.  Revisiting Readability: A Unified Framework for Predicting Text Quality , 2008, EMNLP.

[4]  Alexander S. Yeh,et al.  More accurate tests for the statistical significance of result differences , 2000, COLING.

[5]  G. Miller,et al.  Contexts of antonymous adjectives , 1989, Applied Psycholinguistics.

[6]  Alessandro Lenci,et al.  Identifying hypernyms in distributional semantic spaces , 2012, *SEMEVAL.

[7]  H. Schütze,et al.  Dimensions of meaning , 1992, Supercomputing '92.

[8]  Graeme Hirst,et al.  Computing Word-Pair Antonymy , 2008, EMNLP.

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

[10]  Jörg Tiedemann,et al.  Finding Synonyms Using Automatic Word Alignment and Measures of Distributional Similarity , 2006, ACL.

[11]  David J. Weir,et al.  Characterising Measures of Lexical Distributional Similarity , 2004, COLING.

[12]  Helmut Feldweg,et al.  GermaNet - a Lexical-Semantic Net for German , 1997 .

[13]  Dan I. Moldovan,et al.  Learning Semantic Constraints for the Automatic Discovery of Part-Whole Relations , 2003, NAACL.

[14]  Geoffrey Zweig,et al.  Polarity Inducing Latent Semantic Analysis , 2012, EMNLP.

[15]  Peter D. Turney.  Similarity of Semantic Relations , 2006, CL.

[16]  Christiane Fellbaum,et al.  Co-Occurrence and Antonymy , 1995 .

[17]  L. Murphy.  Semantic Relations and the Lexicon , 2003 .

[18]  Kathleen McKeown,et al.  Aggregated Word Pair Features for Implicit Discourse Relation Disambiguation , 2013, ACL.

[19]  Kai-Wei Chang,et al.  Multi-Relational Latent Semantic Analysis , 2013, EMNLP.

[20]  Qin Lu,et al.  Chasing Hypernyms in Vector Spaces with Entropy , 2014, EACL.

[21]  Daniel Jurafsky,et al.  Learning Syntactic Patterns for Automatic Hypernym Discovery , 2004, NIPS.

[22]  Patrick Pantel,et al.  Espresso: Leveraging Generic Patterns for Automatically Harvesting Semantic Relations , 2006, ACL.

[23]  Ming Zhou,et al.  Identifying Synonyms among Distributionally Similar Words , 2003, IJCAI.

[24]  Bonnie L. Webber,et al.  Genre distinctions for discourse in the Penn TreeBank , 2009, ACL.

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

[26]  Patrick Pantel,et al.  From Frequency to Meaning: Vector Space Models of Semantics , 2010, J. Artif. Intell. Res..

[27]  Christopher D. Manning,et al.  Finding Contradictions in Text , 2008, ACL.

[28]  Roland Schäfer,et al.  Building Large Corpora from the Web Using a New Efficient Tool Chain , 2012, LREC.

[29]  Patrick Pantel,et al.  VerbOcean: Mining the Web for Fine-Grained Semantic Verb Relations , 2004, EMNLP.

[30]  James Richard Curran,et al.  From distributional to semantic similarity , 2004 .

[31]  Graeme Hirst,et al.  Computing Lexical Contrast , 2013, CL.

[32]  Katrin Erk,et al.  A Structured Vector Space Model for Word Meaning in Context , 2008, EMNLP.

[33]  Sanda M. Harabagiu,et al.  Negation, Contrast and Contradiction in Text Processing , 2006, AAAI.

[34]  Carita Paradis,et al.  Discourse functions of antonyms: a cross-linguistic investigation of Swedish and English , 2009 .

[35]  Ani Nenkova,et al.  Automatic sense prediction for implicit discourse relations in text , 2009, ACL.

[36]  Graeme Hirst,et al.  Near-Synonymy and Lexical Choice , 2002, CL.

[37]  Timothy Baldwin,et al.  Experiments on pattern-based relation learning , 2009, CIKM.

[38]  Silvia Bernardini,et al.  The WaCky wide web: a collection of very large linguistically processed web-crawled corpora , 2009, Lang. Resour. Evaluation.

[39]  Ben Hutchinson,et al.  Acquiring the Meaning of Discourse Markers , 2004, ACL.