Technical Question Answering across Tasks and Domains

TL;DR

This paper introduces a deep transfer learning framework for technical question answering that effectively handles cross-task and cross-domain challenges, outperforming existing methods on the TechQA dataset.

Contribution

It proposes an adjustable joint learning approach for document retrieval and reading comprehension tailored to technical QA, addressing data scarcity and domain variability.

Findings

Superior performance on TechQA dataset

Effective handling of limited data and domain shifts

Advancement over state-of-the-art methods

Abstract

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.