12 citations · 49 across the 13 of their papers we have counts for
16 papers
Exploring Distantly-Labeled Rationales in Neural Network Models
Quzhe Huang, Shengqi Zhu, Yansong Feng +1
Recent studies strive to incorporate various human rationales into neural networks to improve model performance, but few pay attention to the quality of the rationales. Most existi…
Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction
Quzhe Huang, Shengqi Zhu, Yansong Feng +3
Document-level Relation Extraction (RE) is a more challenging task than sentence RE as it often requires reasoning over multiple sentences. Yet, human annotators usually use a smal…
Why Machine Reading Comprehension Models Learn Shortcuts?
Yuxuan Lai, Chen Zhang, Yansong Feng +2
Recent studies report that many machine reading comprehension (MRC) models can perform closely to or even better than humans on benchmark datasets. However, existing works indicate…
Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models
Yuxuan Lai, Yijia Liu, Yansong Feng +2
Chinese pre-trained language models usually process text as a sequence of characters, while ignoring more coarse granularity, e.g., words. In this work, we propose a novel pre-trai…
Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis
Xiao Liu, Da Yin, Yansong Feng +2
Causal inference is the process of capturing cause-effect relationship among variables. Most existing works focus on dealing with structured data, while mining causal relationship…
Dialogue History Matters! Personalized Response Selectionin Multi-turn Retrieval-based Chatbots
Juntao Li, Chang Liu, Chongyang Tao +4
Existing multi-turn context-response matching methods mainly concentrate on obtaining multi-level and multi-dimension representations and better interactions between context uttera…