activity
20212026
most citedGALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection

44 citations · 142 across the 17 of their papers we have counts for

collaborators
Showing 2021 · cs.CLShow all

8 papers · 2 filters

cs.CL2021★ 44 cited

GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection

Wanwei He, Yinpei Dai, Yinhe Zheng +9

Pre-trained models have proved to be powerful in enhancing task-oriented dialog systems. However, current pre-training methods mainly focus on enhancing dialog understanding and ge…

cs.CL2021★ 1 cited

Linking-Enhanced Pre-Training for Table Semantic Parsing

Bowen Qin, Lihan Wang, Binyuan Hui +5

Recently pre-training models have significantly improved the performance of various NLP tasks by leveraging large-scale text corpora to improve the contextual representation abilit…

cs.CL2021★ 8 cited

Path-Enhanced Multi-Relational Question Answering with Knowledge Graph Embeddings

Guanglin Niu, Yang Li, Chengguang Tang +6

The multi-relational Knowledge Base Question Answering (KBQA) system performs multi-hop reasoning over the knowledge graph (KG) to achieve the answer. Recent approaches attempt to…

cs.CL2021★ 1 cited

DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings

Che Liu, Rui Wang, Jinghua Liu +3

Learning sentence embeddings from dialogues has drawn increasing attention due to its low annotation cost and high domain adaptability. Conventional approaches employ the siamese-n…

cs.CL2021

MMChat: Multi-Modal Chat Dataset on Social Media

Yinhe Zheng, Guanyi Chen, Xin Liu +1

Incorporating multi-modal contexts in conversation is important for developing more engaging dialogue systems. In this work, we explore this direction by introducing MMChat: a larg…

cs.CL2021★ 4 cited

Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking

Yinpei Dai, Hangyu Li, Yongbin Li +4

Existing dialog state tracking (DST) models are trained with dialog data in a random order, neglecting rich structural information in a dataset. In this paper, we propose to use cu…