Metaphor Detection: Leveraging Culturally Grounded Eventive Information

Abstract

Metaphors are compact packages of information with rich cultural background information. As one of the most powerful linguistic forms with non-literal meaning, metaphor detection in natural language processing can be both challenging and rewarding. We propose an innovative method for metaphor detection and classification leveraging culturally grounded eventive information. This culturally grounded information is organized based on ontological structure, which in turn facilitates further semantic processing of the result of our classification. As a culturally bound ontological system, the Chinese writing system has basic concepts organized according to semantic radicals, which are symbols containing rich eventive information that represent categorical concepts. This paper illustrates the basic design principles of applying ontological structures in metaphor detection by taking into account radicals representing body parts, instruments, materials, and movements. Our approach to leverage the eventive information of the Chinese writing system in metaphor detection is based on the fact that such information is available as an integral part of the writing system of any text. We hypothesize that eventive information can be accessed through the ''embodied'' source domain information represented by the radicals without syntactic processing or annotation. In terms of the theory of metaphor, we further hypothesize that eventive types in the embodied source domain maps to, and hence can help to predict, eventive meaning in the target domain of metaphor. Our studies show that the event information encoded in lexical items can facilitate classification of metaphoric events and identification of metaphors in Chinese texts effectively. We achieved improvements in Chinese metaphor detection over state-of-the-art approaches in our first classification experiment, and our proposed approach is shown to be generalizable in a second experiment involving new sets of characters with the same radicals.

Directionality of Atmospheric Water in Chinese: A Lexical Semantic Study Based on Linguistic Ontology

“…The first deals with language technology and knowledge engineering. We have shown that Chinese writing systems can be leveraged for challenging language processing tasks (Chen et al, 2019). Koptjevskaja-Tamm and Sahlgren (2014) have also demonstrated how to extract more precise weather senses, related to temperature in particular, across different genres using distributional semantic approaches.…”

“…In Hantology, for example, the basic concept of "horse" of the radical 馬 mǎ "horse" serves to connect a network of related concepts through qualia relations: 驩 huān refers to a kind of horse, 騎 qí "to ride" refers to one of the most typical human activities engaging a horse, and 驚 jīng "(to) surprise" originally describes a horse being startled (Chou & Huang, 2010). Such qualia relations have been shown to be psychologically real for speakers of various Sinitic languages (Yang et al, 2018) and can be leveraged in natural language tasks such as metaphor detection (Chen et al, 2019). The current study further investigates the ontological basis of directionality of weather expressions in various Sinitic languages based on Hantology.…”

Identifying Exaggerated Language

“…We begin with an overview of recent work on figurative language processing. For metaphor processing, Rivera et al ( 2020) build a neural network to detect the metaphoricity of adjective-noun pairs using pre-trained word embeddings and word similarity; Zhang et al (2019) use an attention network based on subject-predicate and verb-object relations to identify Chinese verb metaphors; and Chen et al (2019) detect Chinese metaphors using various kinds of cultural background information such as radicals representing body parts, instruments, materials, and movements. For sarcasm detection, Hazarika et al (2018) extract contextual information together with user embeddings in online social media discussions.…”