Determining the Compositionality of Noun-Adjective Pairs with Lexical Variants and Distributional Semantics

English. In this work we employed a set of 26 Italian noun-adjective expressions to test compositionality indices that compare the distributional vector of an expression with the vectors of its lexical variants. These were obtained by replacing the components of the original expression with semantically related words. Our indices performed comparably or better than other compositionality measures reported in the distributional literature. Italiano. In questo lavoro si è utilizzato un set di 26 espressioni italiane nomeaggettivo per testare degli indici di composizionalità che confrontano il vettore distribuzionale di un’espressione con i vettori delle sue varianti lessicali. Queste sono state ottenute sostituendo i componenti dell’espressione di partenza con parole semanticamente correlate. La performance dei nostri indici si è dimostrata comparabile o superiore a quella di altri indici di composizionalità riportati nella letteratura distribuzionale.

[1]  Markus Werning,et al.  The Oxford Handbook of Compositionality , 2012 .

[2]  Afsaneh Fazly,et al.  Unsupervised Type and Token Identification of Idiomatic Expressions , 2009, CL.

[3]  Mirella Lapata,et al.  Composition in Distributional Models of Semantics , 2010, Cogn. Sci..

[4]  Richard A. Harshman,et al.  Indexing by latent semantic indexing analysis , 1990 .

[5]  Cristina Cacciari,et al.  Processing multiword idiomatic strings: Many words in one? , 2014 .

[6]  I. Sag,et al.  Idioms , 2015 .

[7]  Dekang Lin,et al.  Automatic Identification of Non-compositional Phrases , 1999, ACL.

[8]  Cristina Cacciari,et al.  Understanding idiomatic expressions. The contribution of word meanings , 1991 .

[9]  Marco Baroni,et al.  Nouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space , 2010, EMNLP.

[10]  Ioannis Korkontzelos,et al.  Estimating Linear Models for Compositional Distributional Semantics , 2010, COLING.

[11]  Karel Jezek,et al.  Determining Compositionality of Expresssions Using Various Word Space Models and Methods , 2013, CVSM@ACL.

[12]  Barbara H. Partee,et al.  Lexical semantics and compositionality. , 1995 .

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

[14]  Nicholas Asher,et al.  Lexical Meaning in Context - A Web of Words , 2011 .

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

[16]  Carlo Lapucci Dizionario dei modi di dire della lingua italiana , 1979 .

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

[18]  Y. Takane,et al.  Generalized Inverse Matrices , 2011 .

[19]  E. Guevara A Regression Model of Adjective-Noun Compositionality in Distributional Semantics , 2010 .

[20]  Ulrich Heid,et al.  Extraction tools for collocations and their morphosyntactic specificities , 2006, LREC.

[21]  Filip Gralinski Mining the Web for Idiomatic Expressions Using Metalinguistic Markers , 2012, TSD.

[22]  Gennaro Chierchia,et al.  Meaning and Grammar: An Introduction to Semantics , 1990 .

[23]  Stefan Evert,et al.  Corpora and collocations , 2007 .

[24]  John Carroll,et al.  Detecting a Continuum of Compositionality in Phrasal Verbs , 2003, ACL 2003.

[25]  H. Kamp Two theories about adjectives , 2013 .

[26]  Alessandro Lenci,et al.  Lexical Variability and Compositionality: Investigating Idiomaticity with Distributional Semantic Models , 2016, MWE@ACL.

[27]  Nicholas Asher,et al.  Integrating Type Theory and Distributional Semantics: A Case Study on Adjective–Noun Compositions , 2016, CL.

[28]  Aravind K. Joshi,et al.  Measuring the Relative Compositionality of Verb-Noun (V-N) Collocations by Integrating Features , 2005, HLT.

[29]  Alessandro Lenci,et al.  Distributional Memory: A General Framework for Corpus-Based Semantics , 2010, CL.

[30]  Alessandro Lenci,et al.  Distributional semantics in linguistic and cognitive research , 2008 .

[31]  Afsaneh Fazly,et al.  A distributional account of the semantics of multiword expressions , 2008 .

[32]  Colin Bannard A Measure of Syntactic Flexibility for Automatically Identifying Multiword Expressions in Corpora , 2007 .

[33]  Stefan Evert,et al.  Identifying Morphosyntactic Preferences in Collocations , 2004, LREC.

[34]  Luke S. Zettlemoyer,et al.  Automatic Idiom Identification in Wiktionary , 2013, EMNLP.

[35]  Timothy Baldwin,et al.  Multiword Expressions: A Pain in the Neck for NLP , 2002, CICLing.

[36]  Irene Koshik,et al.  Journal of the american society for information science and technology-2012 , 2012 .

[37]  Louise McNally,et al.  Intensionality was only alleged: On adjective-noun composition in distributional semantics , 2013, IWCS.

[38]  Kenneth Ward Church,et al.  Word Association Norms, Mutual Information, and Lexicography , 1989, ACL.

[39]  Dominic Widdows,et al.  Automatic Extraction of Idioms using Graph Analysis and Asymmetric Lexicosyntactic Patterns , 2005, ACL 2005.

[40]  Mirella Lapata,et al.  Dependency-Based Construction of Semantic Space Models , 2007, CL.

[41]  László Dezsö,et al.  Universal Grammar , 1981, Certainty in Action.

[42]  Klaus Krippendorff,et al.  Content Analysis: An Introduction to Its Methodology , 1980 .

[43]  Jussi Piitulainen,et al.  Idiomatic Object Usage and Support Verbs , 1998, COLING-ACL.

[44]  Philipp Cimiano,et al.  Learning Compositionality Functions on Word Embeddings for Modelling Attribute Meaning in Adjective-Noun Phrases , 2017, EACL.

[45]  Zellig S. Harris,et al.  Distributional Structure , 1954 .

[46]  Guy Aston,et al.  Introducing the La Repubblica Corpus: A Large, Annotated, TEI(XML)-compliant Corpus of Newspaper Italian , 2004, LREC.

[47]  Timothy Baldwin,et al.  An Empirical Model of Multiword Expression Decomposability , 2003, ACL 2003.

[48]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[49]  Magnus Sahlgren,et al.  The Distributional Hypothesis , 2008 .

[50]  Ernest Lepore,et al.  The compositionality papers , 2002 .

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

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

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

[54]  Nicholas Asher,et al.  A Generalisation of Lexical Functions for Composition in Distributional Semantics , 2015, ACL.

[55]  Ron Artstein,et al.  Survey Article: Inter-Coder Agreement for Computational Linguistics , 2008, CL.