Impact of Target Word and Context on End-to-End Metonymy Detection

Metonymy is a figure of speech in which an entity is referred to by another related entity. The task of metonymy detection aims to distinguish metonymic tokens from literal ones. Until now, metonymy detection methods attempt to disambiguate only a single noun phrase in a sentence, typically location names or organization names. In this paper, we disambiguate every word in a sentence by reformulating metonymy detection as a sequence labeling task. We also investigate the impact of target word and context on metonymy detection. We show that the target word is less useful for detecting metonymy in our dataset. On the other hand, the entity types that are associated with domain-specific words in their context are easier to solve. This shows that the context words are much more relevant for detecting metonymy.

[1]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[2]  Michael Strube,et al.  A Large Harvested Corpus of Location Metonymy , 2020, LREC.

[3]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[4]  Nigel Collier,et al.  Vancouver Welcomes You! Minimalist Location Metonymy Resolution , 2017, ACL.

[5]  Daniel S. Weld,et al.  Design Challenges for Entity Linking , 2015, TACL.

[6]  Nigel Collier,et al.  Which Melbourne? Augmenting Geocoding with Maps , 2018, ACL.

[7]  Mikko Kurimo,et al.  Part-of-Speech Tagging using Conditional Random Fields: Exploiting Sub-Label Dependencies for Improved Accuracy , 2014, ACL.

[8]  Eunsol Choi,et al.  Neural Metaphor Detection in Context , 2018, EMNLP.

[9]  G. Lakoff,et al.  Metaphors We Live by , 1982 .

[10]  Malvina Nissim,et al.  Metonymy Resolution as a Classification Task , 2002, EMNLP.

[11]  Krister Lindén.  Word Senses , 2005 .

[12]  J. Ardila.  Meaning in Language. An Introduction to Semantics and Pragmatics , 2011 .

[13]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[14]  Gerlof Bouma,et al.  Normalized (pointwise) mutual information in collocation extraction , 2009 .

[15]  Jeffrey Ling,et al.  Matching the Blanks: Distributional Similarity for Relation Learning , 2019, ACL.

[16]  Malvina Nissim,et al.  Syntactic Features and Word Similarity for Supervised Metonymy Resolution , 2003, ACL.

[17]  Eduard H. Hovy,et al.  A Typology of Near-Identity Relations for Coreference (NIDENT) , 2010, LREC.

[18]  Luke Zettlemoyer,et al.  Zero-shot Entity Linking with Dense Entity Retrieval , 2019, ArXiv.

[19]  Brian Roark,et al.  Discriminative Language Modeling with Conditional Random Fields and the Perceptron Algorithm , 2004, ACL.

[20]  Mikhail Khodak,et al.  A Large Self-Annotated Corpus for Sarcasm , 2017, LREC.

[21]  Roberto Navigli,et al.  Word sense disambiguation: A survey , 2009, CSUR.

[22]  Timothy Baldwin,et al.  Target Word Masking for Location Metonymy Resolution , 2020, COLING.

[23]  Michael Strube,et al.  Combining Collocations, Lexical and Encyclopedic Knowledge for Metonymy Resolution , 2009, EMNLP.

[24]  Michael Strube,et al.  Local and Global Context for Supervised and Unsupervised Metonymy Resolution , 2012, EMNLP-CoNLL.

[25]  Jun Okamoto,et al.  Detecting Metonymic Expressions with Associative Information from Words , 2011 .

[26]  Frank Guerin,et al.  End-to-End Sequential Metaphor Identification Inspired by Linguistic Theories , 2019, ACL.

[27]  Udo Hahn,et al.  Understanding metonymies in discourse , 2002, Artif. Intell..

[28]  Dan Klein,et al.  A Joint Model for Entity Analysis: Coreference, Typing, and Linking , 2014, TACL.

[29]  J. Littlemore.  Metonymy: Hidden Shortcuts in Language, Thought and Communication , 2015 .

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

[31]  Takehiro Teraoka.  Metonymy Analysis Using Associative Relations between Words , 2016, LREC.

[32]  G. Nunberg.  The pragmatics of reference , 1978 .

[33]  Christopher D. Manning,et al.  Efficient, Feature-based, Conditional Random Field Parsing , 2008, ACL.