Two-stage Incomplete Utterance Rewriting on Editing Operation
This work solves incomplete utterance rewriting for dialogue systems, though it appears incremental as it builds on prior IUR methods.
The paper tackles incomplete utterance rewriting in dialogues by addressing coreference and ellipsis issues, proposing a two-stage framework (TEO) with editing operations and adversarial perturbation, achieving significant SOTA improvements on three datasets.
Previous work on Incomplete Utterance Rewriting (IUR) has primarily focused on generating rewritten utterances based solely on dialogue context, ignoring the widespread phenomenon of coreference and ellipsis in dialogues. To address this issue, we propose a novel framework called TEO (\emph{Two-stage approach on Editing Operation}) for IUR, in which the first stage generates editing operations and the second stage rewrites incomplete utterances utilizing the generated editing operations and the dialogue context. Furthermore, an adversarial perturbation strategy is proposed to mitigate cascading errors and exposure bias caused by the inconsistency between training and inference in the second stage. Experimental results on three IUR datasets show that our TEO outperforms the SOTA models significantly.