解释来自多个领域的对话中是非问题的答案
Interpreting Answers to Yes-No Questions in Dialogues from Multiple Domains
AI总结：
本文研究大型语言模型在多领域对话中理解是非问题间接答案的挑战，提出三个新领域基准，并基于远程监督与混合训练的方法快速适应新领域，实验显示该方法无负面影响且F1提升达11-34%。
摘要：
人们经常在不明确说出是、否或类似极性关键词的情况下回答是非问题。即使对大型语言模型而言，理解间接答案的含义也具有挑战性。本文研究了来自多个领域对话中的这一问题。我们提出了三个不同领域的新基准：电影剧本、网球访谈和航空客服。我们提出了一种基于远程监督和混合训练的方法，以快速适应新的对话领域。实验结果表明，我们的方法不会产生负面影响，且F1提升高达11-34%。
英文摘要：
People often answer yes-no questions without explicitly saying yes, no, or similar polar keywords. Figuring out the meaning of indirect answers is challenging, even for large language models. In this paper, we investigate this problem working with dialogues from multiple domains. We present new benchmarks in three diverse domains: movie scripts, tennis interviews, and airline customer service. We present an approach grounded on distant supervision and blended training to quickly adapt to a new dialogue domain. Experimental results show that our approach is never detrimental and yields F1 improvements as high as 11-34%.
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。
