Interpreting Indirect Answers to Yes-No Questions in Multiple Languages
This work addresses the challenge of natural language understanding for indirect responses in multilingual contexts, but it is incremental as it builds on existing methods with new data and benchmarks.
The paper tackles the problem of interpreting indirect answers to yes-no questions across multiple languages by releasing new benchmarks in eight languages and demonstrating that direct answers can train models to interpret indirect ones, achieving benefits in monolingual fine-tuning for 5 languages and cross-lingual fine-tuning for all 8 languages.
Yes-no questions expect a yes or no for an answer, but people often skip polar keywords. Instead, they answer with long explanations that must be interpreted. In this paper, we focus on this challenging problem and release new benchmarks in eight languages. We present a distant supervision approach to collect training data. We also demonstrate that direct answers (i.e., with polar keywords) are useful to train models to interpret indirect answers (i.e., without polar keywords). Experimental results demonstrate that monolingual fine-tuning is beneficial if training data can be obtained via distant supervision for the language of interest (5 languages). Additionally, we show that cross-lingual fine-tuning is always beneficial (8 languages).