基于思维链提示的隐式情感推理
Reasoning Implicit Sentiment with Chain-of-Thought Prompting
AI总结：
针对隐式情感分析中观点线索模糊需多跳推理的问题，提出三跳推理思维链框架THOR，通过三步提示逐步推导情感极性，在监督和零样本设置下均大幅提升了最优性能。
摘要：
情感分析系统通常依托输入文本中的关键观点表达来判定给定目标的情感极性，但在隐式情感分析（ISA）中，观点线索以隐含且模糊的形式存在。因此，检测隐式情感需要常识与多跳推理能力来推断潜在的观点意图。受近期思维链（CoT）思路的启发，本研究提出了三跳推理（THOR）CoT框架，以模拟人类处理ISA的推理过程。我们为THOR设计了三步提示原则，逐步诱导出隐式方面、观点，最终得到情感极性。在监督设置下，THOR+Flan-T5（11B）将当前最优（SoTA）的F1值提升了6%以上。更显著的是，THOR+GPT3（175B）在零样本设置下将SoTA的F1值提升了50%以上。代码已开源在https://github.com/scofield7419/THOR-ISA。
英文摘要：
While sentiment analysis systems try to determine the sentiment polarities of given targets based on the key opinion expressions in input texts, in implicit sentiment analysis (ISA) the opinion cues come in an implicit and obscure manner. Thus detecting implicit sentiment requires the common-sense and multi-hop reasoning ability to infer the latent intent of opinion. Inspired by the recent chain-of-thought (CoT) idea, in this work we introduce a Three-hop Reasoning (THOR) CoT framework to mimic the human-like reasoning process for ISA. We design a three-step prompting principle for THOR to step-by-step induce the implicit aspect, opinion, and finally the sentiment polarity. Our THOR+Flan-T5 (11B) pushes the state-of-the-art (SoTA) by over 6% F1 on supervised setup. More strikingly, THOR+GPT3 (175B) boosts the SoTA by over 50% F1 on zero-shot setting. Our code is open at https://github.com/scofield7419/THOR-ISA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
