activity
20172023
most citedHybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion

226 citations · 773 across the 37 of their papers we have counts for

collaborators
Showing 2021Show all

18 papers · 1 filter

cs.CL2021

Achieving Human Parity on Visual Question Answering

Ming Yan, Haiyang Xu, Chenliang Li +14

The Visual Question Answering (VQA) task utilizes both visual image and language analysis to answer a textual question with respect to an image. It has been a popular research topi…

cs.CL2021

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

Enhancing Multilingual Language Model with Massive Multilingual Knowledge Triples

Linlin Liu, Xin Li, Ruidan He +3

Knowledge-enhanced language representation learning has shown promising results across various knowledge-intensive NLP tasks. However, prior methods are limited in efficient utiliz…

cs.CL2021

GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems

Bosheng Ding, Junjie Hu, Lidong Bing +4

Much recent progress in task-oriented dialogue (ToD) systems has been driven by available annotation data across multiple domains for training. Over the last few years, there has b…

cs.CL2021

MReD: A Meta-Review Dataset for Structure-Controllable Text Generation

Chenhui Shen, Liying Cheng, Ran Zhou +3

When directly using existing text generation datasets for controllable generation, we are facing the problem of not having the domain knowledge and thus the aspects that could be c…

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…