Metaphor Generation with Conceptual Mappings
| Autor: | Kevin Stowe, Smaranda Muresan, Iryna Gurevych, Tuhin Chakrabarty, Nanyun Peng |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language Metaphor Computer science business.industry I.2.7 Deep learning media_common.quotation_subject Conceptual metaphor computer.software_genre Expression (mathematics) Literal (computer programming) Artificial intelligence FrameNet Control (linguistics) business Computation and Language (cs.CL) computer Natural language processing Sentence media_common |
| Zdroj: | ACL/IJCNLP (1) |
| DOI: | 10.18653/v1/2021.acl-long.524 |
| Popis: | Generating metaphors is a difficult task as it requires understanding nuanced relationships between abstract concepts. In this paper, we aim to generate a metaphoric sentence given a literal expression by replacing relevant verbs. Guided by conceptual metaphor theory, we propose to control the generation process by encoding conceptual mappings between cognitive domains to generate meaningful metaphoric expressions. To achieve this, we develop two methods: 1) using FrameNet-based embeddings to learn mappings between domains and applying them at the lexical level (CM-Lex), and 2) deriving source/target pairs to train a controlled seq-to-seq generation model (CM-BART). We assess our methods through automatic and human evaluation for basic metaphoricity and conceptual metaphor presence. We show that the unsupervised CM-Lex model is competitive with recent deep learning metaphor generation systems, and CM-BART outperforms all other models both in automatic and human evaluations. Comment: 13 pages, 3 figures, to be published in the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|