TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Dialogue Rewriting	Multi-Rewrite	RUN+BERT	Rewriting F3	47.7	# 1
Dialogue Rewriting	Rewrite	RUN+BERT	ROUGE-L	93.5	# 1

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/incomplete-utterance-rewriting-as-semantic/dialogue-rewriting-on-multi-rewrite)](https://paperswithcode.com/sota/dialogue-rewriting-on-multi-rewrite?p=incomplete-utterance-rewriting-as-semantic)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/incomplete-utterance-rewriting-as-semantic/dialogue-rewriting-on-rewrite)](https://paperswithcode.com/sota/dialogue-rewriting-on-rewrite?p=incomplete-utterance-rewriting-as-semantic)`

Incomplete Utterance Rewriting as Semantic Segmentation

EMNLP 2020 · Qian Liu, Bei Chen, Jian-Guang Lou, Bin Zhou, Dongmei Zhang ·

Recent years the task of incomplete utterance rewriting has raised a large attention. Previous works usually shape it as a machine translation task and employ sequence to sequence based architecture with copy mechanism. In this paper, we present a novel and extensive approach, which formulates it as a semantic segmentation task. Instead of generating from scratch, such a formulation introduces edit operations and shapes the problem as prediction of a word-level edit matrix. Benefiting from being able to capture both local and global information, our approach achieves state-of-the-art performance on several public datasets. Furthermore, our approach is four times faster than the standard approach in inference.