paper-with-me

Dialogue Rewriting

3개 벤치마크 · 논문 7편 · 이 태스크의 논문 보기 →

Benchmarks

Multi-Rewrite

결과 3개

CANARD

결과 1개

Rewrite

결과 1개

Most implemented

Papers

Friend-training: Learning from Models of Different but Related Tasks

2023-01-31 · Mian Zhang, Lifeng Jin, Linfeng Song, Haitao Mi 외

Current self-training methods such as standard self-training, co-training, tri-training, and others often focus on improving model performance on a single task, utilizing differences in input features, model architecture…

Dialogue RewritingDialogue UnderstandingSemantic Role Labeling

RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging

2021-11-01 · EMNLP 2021 11 · Jie Hao, Linfeng Song, LiWei Wang, Kun Xu 외

The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context. Until now, the existing models for this task suffer from the robustness issue, i.…

Dialogue RewritingText Generation

Robust Dialogue Utterance Rewriting as Sequence Tagging

2020-12-29 · Jie Hao, Linfeng Song, LiWei Wang, Kun Xu 외

The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context. Until now, the existing models for this task suffer from the robustness issue, i.…

Dialogue RewritingText Generation

Semantic Role Labeling Guided Multi-turn Dialogue ReWriter

2020-10-03 · EMNLP 2020 11 · Kun Xu, Haochen Tan, Linfeng Song, Han Wu 외

For multi-turn dialogue rewriting, the capacity of effectively modeling the linguistic knowledge in dialog context and getting rid of the noises is essential to improve its performance. Existing attentive models attend t…

Dialogue RewritingSemantic Role Labeling

Incomplete Utterance Rewriting as Semantic Segmentation

2020-09-28 · EMNLP 2020 11 · Qian Liu, Bei Chen, Jian-Guang Lou, Bin Zhou 외

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. …

Context Query ReformulationDialogue RewritingSegmentationTranslation

SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration

2020-08-04 · Mengzuo Huang, Feng Li, Wuhe Zou, Weidong Zhang

Dialogue systems in open domain have achieved great success due to the easily obtained single-turn corpus and the development of deep learning, but the multi-turn scenario is still a challenge because of the frequent cor…

Dialogue RewritingText Generation

전체 7편 보기 →