238 citations · 292 across the 16 of their papers we have counts for
14 papers · 1 filter
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…
Meaningful Answer Generation of E-Commerce Question-Answering
Shen Gao, Xiuying Chen, Zhaochun Ren +2
In e-commerce portals, generating answers for product-related questions has become a crucial task. In this paper, we focus on the task of product-aware answer generation, which lea…
Learning to Respond with Your Favorite Stickers: A Framework of Unifying Multi-Modality and User Preference in Multi-Turn Dialog
Shen Gao, Xiuying Chen, Li Liu +2
Stickers with vivid and engaging expressions are becoming increasingly popular in online messaging apps, and some works are dedicated to automatically select sticker response by ma…
Knowledge-Grounded Dialogue Generation with Pre-trained Language Models
Xueliang Zhao, Wei Wu, Can Xu +3
We study knowledge-grounded dialogue generation with pre-trained language models. To leverage the redundant external knowledge under capacity constraint, we propose equipping respo…
Cross-Lingual Low-Resource Set-to-Description Retrieval for Global E-Commerce
Juntao Li, Chang Liu, Jian Wang +5
With the prosperous of cross-border e-commerce, there is an urgent demand for designing intelligent approaches for assisting e-commerce sellers to offer local products for consumer…
Neighborhood Matching Network for Entity Alignment
Yuting Wu, Xiao Liu, Yansong Feng +2
Structural heterogeneity between knowledge graphs is an outstanding challenge for entity alignment. This paper presents Neighborhood Matching Network (NMN), a novel entity alignmen…
Integrating Relation Constraints with Neural Relation Extractors
Yuan Ye, Yansong Feng, Bingfeng Luo +2
Recent years have seen rapid progress in identifying predefined relationship between entity pairs using neural networks NNs. However, such models often make predictions for each en…
Transformation of Dense and Sparse Text Representations
Wenpeng Hu, Mengyu Wang, Bing Liu +5
Sparsity is regarded as a desirable property of representations, especially in terms of explanation. However, its usage has been limited due to the gap with dense representations.…
Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs
Yuting Wu, Xiao Liu, Yansong Feng +3
Entity alignment is the task of linking entities with the same real-world identity from different knowledge graphs (KGs), which has been recently dominated by embedding-based metho…