Mining Clues from Incomplete Utterance: A Query-enhanced Network for Incomplete Utterance Rewriting

TL;DR

This paper introduces QUEEN, a query-enhanced network that explicitly models semantic structural information to improve incomplete utterance rewriting, achieving state-of-the-art results.

Contribution

It proposes a novel query template and an edit operation scoring network to explicitly incorporate semantic structural knowledge in utterance rewriting.

Findings

Achieves state-of-the-art performance on multiple datasets.

Effectively models semantic structure between utterances.

Utilizes a query template to guide the rewriting process.

Abstract

Incomplete utterance rewriting has recently raised wide attention. However, previous works do not consider the semantic structural information between incomplete utterance and rewritten utterance or model the semantic structure implicitly and insufficiently. To address this problem, we propose a QUEry-Enhanced Network (QUEEN). Firstly, our proposed query template explicitly brings guided semantic structural knowledge between the incomplete utterance and the rewritten utterance making model perceive where to refer back to or recover omitted tokens. Then, we adopt a fast and effective edit operation scoring network to model the relation between two tokens. Benefiting from proposed query template and the well-designed edit operation scoring network, QUEEN achieves state-of-the-art performance on several public datasets.