让模型理解隐喻，不靠揣测动机，只看修辞策略
$(RSA)^2$: A Rhetorical-Strategy-Aware Rational Speech Act Framework for Figurative Language Understanding
- 引入修辞策略建模，让语言理解更贴近人类推理
- 在新数据集PragMega+上达到当前最佳表现
- 无需假设说话人情绪或意图，适合通用对话系统
隐喻语言（如反语、夸张、轻描淡写）在人类交流中无处不在，其字面意义与真实意图常不一致。理性言语行为（RSA）框架通过显式建模说话人意图，是概率语用学中最广泛使用的理论，但现有实现要么无法处理隐喻表达，要么需针对具体场景建模说话人使用隐喻的隐含动机（如表达喜悦或不满）。本文提出修辞策略感知的RSA框架$(RSA)^2$，通过考虑说话人采用的修辞策略来建模隐喻语言使用。实验表明，$(RSA)^2$可在不建模说话人非字面表达动机的前提下，实现与人类兼容的非字面语句解释。结合大语言模型，在本文提出的全新反语理解数据集PragMega+的反语子集上达到当前最优性能。
原文摘要 · Abstract (English)
Figurative language (e.g., irony, hyperbole, understatement) is ubiquitous in human communication, resulting in utterances where the literal and the intended meanings do not match. The Rational Speech Act (RSA) framework, which explicitly models speaker intentions, is the most widespread theory of probabilistic pragmatics, but existing implementations are either unable to account for figurative expressions or require modeling the implicit motivations for using figurative language (e.g., to express joy or annoyance) in a setting-specific way. In this paper, we introduce the Rhetorical-Strategy-Aware RSA $(RSA)^2$ framework which models figurative language use by considering a speaker's employed rhetorical strategy. We show that $(RSA)^2$ enables human-compatible interpretations of non-literal utterances without modeling a speaker's motivations for being non-literal. Combined with LLMs, it achieves state-of-the-art performance on the ironic split of PragMega+, a new irony interpretation dataset introduced in this study.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。