Being neighbourly: Neural metaphor identification in discourse

Existing approaches to metaphor processing typically rely on local features, such as immediate lexico-syntactic contexts or information within a given sentence. However, a large body of corpus-linguistic research suggests that situational information and broader discourse properties influence metaphor production and comprehension. In this paper, we present the first neural metaphor processing architecture that models a broader discourse through the use of attention mechanisms. Our models advance the state of the art on the all POS track of the 2018 VU Amsterdam metaphor identification task. The inclusion of discourse-level information yields further significant improvements.

[1]  Sanja Fidler,et al.  Skip-Thought Vectors , 2015, NIPS.

[2]  Jeremy H. Clear,et al.  The British national corpus , 1993 .

[3]  Ekaterina Shutova,et al.  Grasping the Finer Point: A Supervised Similarity Network for Metaphor Detection , 2017, EMNLP.

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

[5]  Tomek Strzalkowski,et al.  Using Imageability and Topic Chaining to Locate Metaphors in Linguistic Corpora , 2013, SBP.

[6]  Tyler Marghetis,et al.  Literal and Metaphorical Senses in Compositional Distributional Semantic Models , 2016, ACL.

[7]  Andreas Musolff,et al.  Mirror Images of Europe: Metaphors in the Public Debate About Europe in Britain and Germany , 2000 .

[8]  Beata Beigman Klebanov,et al.  A Report on the 2018 VUA Metaphor Detection Shared Task , 2018, Fig-Lang@NAACL-HLT.

[9]  Helen Yannakoudakis,et al.  Learning Outside the Box: Discourse-level Features Improve Metaphor Identification , 2019, NAACL.

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

[11]  Stephen Clark,et al.  Modelling metaphor with attribute-based semantics , 2017, EACL.

[12]  Ekaterina Shutova,et al.  Computational approaches to figurative language , 2011 .

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

[14]  Yorick Wilks,et al.  Automatic Metaphor Detection using Large-Scale Lexical Resources and Conventional Metaphor Extraction , 2013 .

[15]  Beata Beigman Klebanov,et al.  Semantic classifications for detection of verb metaphors , 2016, ACL.

[16]  Chuhan Wu,et al.  Neural Metaphor Detecting with CNN-LSTM Model , 2018, Fig-Lang@NAACL-HLT.

[17]  Mehdi Ghanimifard,et al.  Bigrams and BiLSTMs Two Neural Networks for Sequential Metaphor Detection , 2018, Fig-Lang@NAACL-HLT.

[18]  Carolyn Penstein Rosé,et al.  Metaphor Detection in Discourse , 2015, SIGDIAL Conference.

[19]  Gerard J. Steen,et al.  A method for linguistic metaphor identification : from MIP to MIPVU , 2010 .

[20]  Martha Lewis,et al.  Modelling the interplay of metaphor and emotion through multitask learning , 2019, EMNLP.

[21]  Diyi Yang,et al.  Hierarchical Attention Networks for Document Classification , 2016, NAACL.

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

[23]  Yair Neuman,et al.  Literal and Metaphorical Sense Identification through Concrete and Abstract Context , 2011, EMNLP.

[24]  Alex Lascarides,et al.  Metaphor in Discourse , 1995 .

[25]  Carolyn Penstein Rosé,et al.  Effects of Situational Factors on Metaphor Detection in an Online Discussion Forum , 2015 .

[26]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

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

[28]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.