Being neighbourly: Neural metaphor identification in discourse

Abstract

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.

Neural Metaphor Detection with Visibility Embeddings

“…Impressive results 1 were presented in the 2018 Metaphor Detection Shared Task (Leong et al, 2018), with most of the groups using neural models with other linguistic elements like POS tags, Word-Net features, concreteness scores and more (Wu et al, 2018;Swarnkar and Singh, 2018;Pramanick et al, 2018;Bizzoni and Ghanimifard, 2018), as well as in the more recent 2020 Shared Task , with the majority of groups using some variation of BERT in addition to the other features Gao and Zhang, 2002;Kuo and Carpuat, 2020;Torres Rivera et al, 2020;Kumar and Sharma, 2020;Hall Maudslay et al, 2020;Stemle and Onysko, 2020;Liu et al, 2020;Brooks and Youssef, 2020;Alnafesah et al, 2020;Wan et al, 2020;Dankers et al, 2020).…”

“…yet not directly comparable to ours, since they used different train-test separations and evaluation, seeDankers et al (2020) …”

Verb Metaphor Detection via Contextual Relation Learning

“…Recently, Transformer based pre-trained language models become the most popular architecture in the metaphor detection shared task . Multitask learning (Dankers et al, 2019;Rohanian et al, 2020; and discourse context (Dankers et al, 2020) have been exploited as well. Discussion The grammatical relation-level and token-level metaphor detection consider different aspects of information.…”

Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics

“…Impressive results 1 were presented in the 2018 Metaphor Detection Shared Task (Leong et al, 2018), with most of the groups using neural models with other linguistic elements like POS tags, Word-Net features, concreteness scores and more Swarnkar and Singh, 2018;Pramanick et al, 2018;Bizzoni and Ghanimifard, 2018), as well as in the more recent 2020 Shared Task , with the majority of groups using some variation of BERT in addition to the other features Gao and Zhang, 2002;Kuo and Carpuat, 2020;Torres Rivera et al, 2020;Kumar and Sharma, 2020;Hall Maudslay et al, 2020;Stemle and Onysko, 2020;Brooks and Youssef, 2020;Chen et al, 2020;Alnafesah et al, 2020;Wan et al, 2020;Dankers et al, 2020).…”