Technical Question Answering across Tasks and Domains
This work addresses technical support automation for users in specialized domains, representing an incremental advance in adapting QA methods to niche areas.
The paper tackles the problem of technical question answering by proposing a deep transfer learning framework that addresses challenges like limited data and low overlap between questions and answers, achieving superior performance on the TechQA benchmark compared to state-of-the-art methods.
Building automatic technical support system is an important yet challenge task. Conceptually, to answer a user question on a technical forum, a human expert has to first retrieve relevant documents, and then read them carefully to identify the answer snippet. Despite huge success the researchers have achieved in coping with general domain question answering (QA), much less attentions have been paid for investigating technical QA. Specifically, existing methods suffer from several unique challenges (i) the question and answer rarely overlaps substantially and (ii) very limited data size. In this paper, we propose a novel framework of deep transfer learning to effectively address technical QA across tasks and domains. To this end, we present an adjustable joint learning approach for document retrieval and reading comprehension tasks. Our experiments on the TechQA demonstrates superior performance compared with state-of-the-art methods.