CLJun 2, 2021

Metaphor Generation with Conceptual Mappings

arXiv:2106.01228v1723 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of automated metaphor generation for natural language processing applications, but it is incremental as it builds on existing theories and methods.

The paper tackled the problem of generating metaphors from literal expressions by replacing verbs, using conceptual mappings to control generation, and found that their CM-BART model outperformed other models in evaluations.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes