Self-Attention for Incomplete Utterance Rewriting
This addresses the problem of improving text comprehension in NLP for tasks like dialogue systems, but it is incremental as it builds on existing transformer-based approaches.
The paper tackled incomplete utterance rewriting by proposing a method that extracts coreference and omission relationships from transformer self-attention weights to edit text, achieving competitive results on public datasets.
Incomplete utterance rewriting (IUR) has recently become an essential task in NLP, aiming to complement the incomplete utterance with sufficient context information for comprehension. In this paper, we propose a novel method by directly extracting the coreference and omission relationship from the self-attention weight matrix of the transformer instead of word embeddings and edit the original text accordingly to generate the complete utterance. Benefiting from the rich information in the self-attention weight matrix, our method achieved competitive results on public IUR datasets.