A hybrid representation-based simile component extraction
- PDF / 1,371,829 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 86 Downloads / 177 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
A hybrid representation-based simile component extraction Da Ren1 • Pengfei Zhang1 • Qing Li2 • Xiaohui Tao3 • Junying Chen1 • Yi Cai1 Received: 26 August 2019 / Accepted: 24 February 2020 Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Simile, a special type of metaphor, can help people to express their ideas more clearly. Simile component extraction is to extract tenors and vehicles from sentences. This task has a realistic significance since it is useful for building cognitive knowledge base. With the development of deep neural networks, researchers begin to apply neural models to component extraction. Simile components should be in cross-domain. According to our observations, words in cross-domain always have different concepts. Thus, concept is important when identifying whether two words are simile components or not. However, existing models do not integrate concept into their models. It is difficult for these models to identify the concept of a word. What’s more, corpus about simile component extraction is limited. There are a number of rare words or unseen words, and the representations of these words are always not proper enough. Exiting models can hardly extract simile components accurately when there are low-frequency words in sentences. To solve these problems, we propose a hybrid representation-based component extraction (HRCE) model. Each word in HRCE is represented in three different levels: word level, concept level and character level. Concept representations (representations in concept level) can help HRCE to identify the words in cross-domain more accurately. Moreover, with the help of character representations (representations in character levels), HRCE can represent the meaning of a word more properly since words are consisted of characters and these characters can partly represent the meaning of words. We conduct experiments to compare the performance between HRCE and existing models. The experiment results show that HRCE significantly outperforms current models. Keywords Simile component Concept Character
1 Introduction Metaphor is commonly used in human conversations and researches. It is as a matter of cross-domain mappings in conceptual structure which are expressed in language [25]. Metaphor can help people to express their ideas more accurately. Moreover, people can understand the thought of other people more easily with the help of metaphor. Interpreting metaphors is an integral and inescapable process in human understanding of natural language [6]. Therefore, there are growing researches about metaphor analyses [17, 25, 37]. & Yi Cai [email protected] 1
South China University of Technology, Guangzhou, China
2
The Hong Kong Polytechnic University, Hong Kong, China
3
The University of Southern Queensland, Toowoomba, Australia
Researchers begin to analyze metaphor by recognizing simile [25]. Simile is a special type of metaphor. There are explicit markers (e.g., ‘‘as’’, ‘‘like’’) which are also
Data Loading...
