Multi-Task Learning for Metaphor Detection with Graph Convolutional Neural Networks and Word Sense Disambiguation

Abstract

The current deep learning works on metaphor detection have only considered this task independently, ignoring the useful knowledge from the related tasks and knowledge resources. In this work, we introduce two novel mechanisms to improve the performance of the deep learning models for metaphor detection. The first mechanism employs graph convolutional neural networks (GCN) with dependency parse trees to directly connect the words of interest with their important context words for metaphor detection. The GCN networks in this work also present a novel control mechanism to filter the learned representation vectors to retain the most important information for metaphor detection. The second mechanism, on the other hand, features a multi-task learning framework that exploits the similarity between word sense disambiguation and metaphor detection to transfer the knowledge between the two tasks. The extensive experiments demonstrate the effectiveness of the proposed techniques, yielding the state-of-the-art performance over several datasets.

Neural Metaphor Detection with Visibility Embeddings

“…To maintain consistency with the results by Gao et al (2018) and Le et al (2020), we present our results both on their prechosen sets, as well as on randomly chosen splits (rand-CV).…”

“…We noticed that in general, higher F1-scores are gained for splits where the training set and evaluation set contain instances of the same verbs. Previously Model P R F1 Gao et al (2018) 79.1 73.5 75.6 Le et al (2020) 79.7 80.5 79.6 Mao et al (2019) 77. Mao et al (2019).…”

“…The current state-of-the-art in metaphor detection is achieved by neural methods, enriched with contextual word embeddings (such as ELMo (Peters et al, 2018) and BERT (Devlin et al, 2019)), and commonly combined with varied linguistic features and metrics. Some notable results are the ones by Gao et al (2018) who used ELMo and BiLSTM, Mao et al (2019) who also experimented with BERT and features that rely on human metaphor processing, Dankers et al (2019) who performed joint learning with emotion prediction, and Le et al (2020) who used graph convolutional neural networks with dependency parse trees.…”

Enhancing Metaphor Detection by Gloss-based Interpretations

“…Gao et al (2018) and Mao et al (2019) respectively utilized GloVe (Pennington et al, 2014) and ELMo (Peters et al, 2018) embeddings. Le et al (2020) proposed to construct a graph CNN guided by dependency trees of sentences for metaphor detection and to construct a multi-task learning framework for the WSD task, utilizing the knowledge from WSD to improve metaphor detection. Instead of treating metaphor detection as a sequence tagging task, Su et al (2020) proposed a novel reading comprehension paradigm based on a pre-trained language model, using features from POS tags and local texts.…”

A Report on the 2020 VUA and TOEFL Metaphor Detection Shared Task

“…The best results posted for the 2020 shared task are the new state-of-the-art for both VUA 7 and TOEFL corpora. 7 While a number of recent systems were evaluted on VUA data (Le et al, 2020;Dankers et al, 2019;Mao et al, 2019;Gao et al, 2018), their results are not directly comparable to the shared task, since they evaluated on all parts of speech, including function words. See Dankers et al (2020) for a discussion.…”