activity
20202022
most citedDivide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents

2 citations · 6 across the 6 of their papers we have counts for

collaborators

8 papers

cs.CV20222 cited

Increasing Visual Awareness in Multimodal Neural Machine Translation from an Information Theoretic Perspective

Baijun Ji, Tong Zhang, Yicheng Zou +2

Multimodal machine translation (MMT) aims to improve translation quality by equipping the source sentence with its corresponding image. Despite the promising performance, MMT model…

cs.CL20221 cited

MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective

Xiao Wang, Shihan Dou, Limao Xiong +6

NER model has achieved promising performance on standard NER benchmarks. However, recent studies show that previous approaches may over-rely on entity mention information, resultin…

cs.CL20222 cited

Divide and Conquer: Text Semantic Matching with Disentangled Keywords and Intents

Yicheng Zou, Hongwei Liu, Tao Gui +5

Text semantic matching is a fundamental task that has been widely used in various scenarios, such as community question answering, information retrieval, and recommendation. Most s…

cs.CL20211 cited

Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training

Zhengyan Li, Yicheng Zou, Chong Zhang +2

Aspect-based sentiment analysis aims to identify the sentiment polarity of a specific aspect in product reviews. We notice that about 30% of reviews do not contain obvious opinion…

cs.CL2021

Low-Resource Dialogue Summarization with Domain-Agnostic Multi-Source Pretraining

Yicheng Zou, Bolin Zhu, Xingwu Hu +2

With the rapid increase in the volume of dialogue data from daily life, there is a growing demand for dialogue summarization. Unfortunately, training a large summarization model is…

cs.CL2021

Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems

Yicheng Zou, Zhihua Liu, Xingwu Hu +1

Human dialogue contains evolving concepts, and speakers naturally associate multiple concepts to compose a response. However, current dialogue models with the seq2seq framework lac…