Enhancing Metaphor Detection by Gloss-based Interpretations

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 1971–1981 August 1–6, 2021. ©2021 Association for Computational Linguistics 1971 Enhancing Metaphor Detection by Gloss-based Interpretations Hai Wan1, Jinxia Lin1, Jianfeng Du2,3⇤, Dawei Shen1, Manrong Zhang1 1 School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou 510006, P.R.China 2 Guangzhou Key Laboratory of Multilingual Intelligent Processing, Guangdong University of Foreign Studies, Guangzhou 510006, P.R.China 3 Pazhou Lab, Guangzhou 510330, P.R.China wanhai@mail.sysu.edu.cn, jfdu@gdufs.edu.cn, {linjx36, shendw5, zhangmr7}@mail2.sysu.edu.cn Abstract This paper focuses on utilizing metaphor inter- pretation to enhance metaphor detection. Con- sidering that existing approaches to metaphor interpretation are limited by ambiguous mean- ings of the metaphorical substitute words, this paper proposes a novel interpretation mechanism that utilizes glosses to interpret metaphorical words. Since there is no dataset annotated for both metaphor detection and metaphor interpretation, we enhance three datasets TroFi, VUA, and PSUCMC from the field of metaphor detection with gloss anno- tations. Accordingly, we develop a model for jointly conducting metaphor detection and gloss-based interpretation (named MDGI- Joint for short). Experimental results demon- strate that MDGI-Joint outperforms state-of- the-art models on all the three enhanced datasets and that gloss-based metaphor inter- pretation benefits metaphor detection.1 1 Introduction Metaphor has been defined as words or other lin- guistic expressions representing another concept with the language from a more concrete conceptual domain (K¨ovecses and Zolt´an, 2002; Lagerwerf and Meijers, 2008). According to existing studies on metaphor (K¨ovecses and Zolt´an, 2002; Steen, 2010), metaphor has been used so frequently in daily language that it almost occurs in one out of three natural language sentences. Metaphor detection aims to identify all metaphorical words in given texts and has been demonstrated to be of great value in many Natural Language Processing (NLP) tasks, such as machine translation (Mao et al., 2018), machine reading comprehension (Shutova et al., 2013), etc. There- ⇤Corresponding author 1Source code and datasets are available at https:// github.com/sysulic/MDGI. Example : The stroke clouded memories of her youth. Metaphorical word : clouded (Mao, Lin, and Guerin 2018) interpretation : change Meanings of change : make different, remove or replace the coverings of, , become deeper in tone Gloss as interpretation : to make unclear or confused Figure 1: An example for metaphor detection, where the word clouded is a metaphorical word (highlighted in bold and underline). Interpretation by a substitute word (highlighted in bold) is computed by (Mao et al., 2018). Gloss as interpretation (highlighted in blue bold italics) is picked from the Merriam Webster dictionary. fore, metaphor detection has drawn increasing inter- ests in recent years. There have emerged a number of methods for metaphor detection, including SEQ (Gao et al., 2018), RNN HG (Mao et al., 2019), RNN MHCA (Mao et al., 2019), MUL GCN (Le et al., 2020), DeepMet (Su et al., 2020), etc. To capture the meanings of metaphorical words, metaphor interpretation has also been studied, which paraphrases metaphorical expressions into literal expressions that maintain the intended mean- ings of given texts (Mao et al., 2018). Existing approaches …

Content truncated to 500 words