Interpreting Answers to Yes-No Questions in Dialogues from Multiple Domains
This work addresses a specific challenge in natural language understanding for dialogue systems, offering incremental improvements in domain adaptation.
The paper tackled the problem of interpreting indirect yes-no answers in dialogues across multiple domains, achieving F1 improvements of 11-34% using a distant supervision and blended training approach.
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%.