Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base

TL;DR

This paper introduces a multi-task learning framework for conversational question answering over large knowledge bases, addressing error propagation and supervision sharing issues in neural semantic parsing.

Contribution

It proposes a novel multi-task learning approach with a pointer-equipped semantic parser and type-aware entity detection, improving performance on large-scale datasets.

Findings

F1 score improved from 67% to 79%.

Shared supervision reduces error propagation.

Effective handling of coreference in conversations.

Abstract

We consider the problem of conversational question answering over a large-scale knowledge base. To handle huge entity vocabulary of a large-scale knowledge base, recent neural semantic parsing based approaches usually decompose the task into several subtasks and then solve them sequentially, which leads to following issues: 1) errors in earlier subtasks will be propagated and negatively affect downstream ones; and 2) each subtask cannot naturally share supervision signals with others. To tackle these issues, we propose an innovative multi-task learning framework where a pointer-equipped semantic parsing model is designed to resolve coreference in conversations, and naturally empower joint learning with a novel type-aware entity detection model. The proposed framework thus enables shared supervisions and alleviates the effect of error propagation. Experiments on a large-scale conversational question answering dataset containing 1.6M question answering pairs over 12.8M entities show that the proposed framework improves overall F1 score from 67% to 79% compared with previous state-of-the-art work.