Leveraging Eventive Information for Better Metaphor Detection and Classification

Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pages 36–46, Vancouver, Canada, August 3 - August 4, 2017. c⃝2017 Association for Computational Linguistics Leveraging Eventive Information for Better Metaphor Detection and Classification I-Hsuan Chen1, Yunfei Long2, Qin Lu2, Chu-Ren Huang1 1Department of Chinese & Bilingual Studies, The Hong Kong Polytechnic University {ihsuan.chen, churen.huang}@polyu.edu.hk 2Department of Computing, The Hong Kong Polytechnic University {csylong, csluqin}@comp.polyu.edu.hk Abstract Metaphor detection has been both chal- lenging and rewarding in natural language processing applications. This study offers a new approach based on eventive infor- mation in detecting metaphors by leverag- ing the Chinese writing system, which is a culturally bound ontological system orga- nized according to the basic concepts rep- resented by radicals. As such, the infor- mation represented is available in all Chi- nese text without pre-processing. Since metaphor detection is another culturally based conceptual representation, we hy- pothesize that sub-textual information can facilitate the identification and classifica- tion of the types of metaphoric events de- noted in Chinese text. We propose a set of syntactic conditions crucial to event struc- tures to improve the model based on the classification of radical groups. With the proposed syntactic conditions, the model achieves a performance of 0.8859 in terms of F-scores, making 1.7% of improvement than the same classifier with only Bag-of- word features. Results show that eventive information can improve the effectiveness of metaphor detection. Event information is rooted in every language, and thus this approach has a high potential to be applied to metaphor detection in other languages. 1 Introduction Metaphors are a cross linguistic phenomenon in everyday language as shown in a great amount of corpus linguistic and experimental studies. The Conceptual Metaphor Theory (Lakoff, 1989; Lakoff and Johnson, 1981) shows how linguistic expressions reflect the mapping of two conceptu- al domains. For example, the expression I see what you mean instantiates the conceptual meta- phor of KNOWING IS SEEING. The phrase is the result of mapping the source domain SEE- ING, which is embodied daily experience onto the target domain, KNOWING, as exemplified in the examples of shed some light on this, an illu- minating article, and take a close look. Due to the pervasive use of metaphors, there is an enormous amount of studies in the techniques of detecting metaphors. Relevant studies of detecting meta- phors primarily rely on contextual information. This study provides a novel approach to detect and classify metaphors by analyzing eventive in- formation. Concepts can be classified into a wide array of event types according to ontology, the organization of knowledge (Huang et al., 2007). Eventive information thus can be applied to the classification of metaphors, which concern map- pings of conceptual structures from a source do- main to a target domain. The classification of metaphoric and literal senses has been approached by different methods such as vector-space models with distributional statistics (Hovy et al., 2013; Tsvetkov et al., 2014) and compositional distributional semantic models (CDSMs) (Kartsaklis and Sadrzadeh, 2013a). Most of the studies …

Content truncated to 500 words