DoQA -- Accessing Domain-Specific FAQs via Conversational QA
This work addresses the challenge of accessing domain-specific FAQ information through conversational interfaces, which is incremental by extending QA to multi-domain FAQs with a new dataset and retrieval setup.
The authors tackled the problem of building conversational question answering systems for domain-specific FAQ sites by introducing DoQA, a dataset of 2,437 dialogues and 10,917 QA pairs collected from Stack Exchange, which enables more coherent and natural conversations. They showed that transfer learning from Wikipedia QA and fine-tuning on a single FAQ domain allows high-quality systems without in-domain data, achieving good results in a realistic information retrieval scenario, though human performance remains higher.
The goal of this work is to build conversational Question Answering (QA) interfaces for the large body of domain-specific information available in FAQ sites. We present DoQA, a dataset with 2,437 dialogues and 10,917 QA pairs. The dialogues are collected from three Stack Exchange sites using the Wizard of Oz method with crowdsourcing. Compared to previous work, DoQA comprises well-defined information needs, leading to more coherent and natural conversations with less factoid questions and is multi-domain. In addition, we introduce a more realistic information retrieval(IR) scenario where the system needs to find the answer in any of the FAQ documents. The results of an existing, strong, system show that, thanks to transfer learning from a Wikipedia QA dataset and fine tuning on a single FAQ domain, it is possible to build high quality conversational QA systems for FAQs without in-domain training data. The good results carry over into the more challenging IR scenario. In both cases, there is still ample room for improvement, as indicated by the higher human upperbound.