85 citations · 633 across the 51 of their papers we have counts for
8 papers · 1 filter
Multi-Paragraph Reasoning with Knowledge-enhanced Graph Neural Network
Deming Ye, Yankai Lin, Zhenghao Liu +2
Multi-paragraph reasoning is indispensable for open-domain question answering (OpenQA), which receives less attention in the current OpenQA systems. In this work, we propose a know…
HighwayGraph: Modelling Long-distance Node Relations for Improving General Graph Neural Network
Deli Chen, Xiaoqian Liu, Yankai Lin +4
Graph Neural Networks (GNNs) are efficient approaches to process graph-structured data. Modelling long-distance node relations is essential for GNN training and applications. Howev…
Guiding Non-Autoregressive Neural Machine Translation Decoding with Reordering Information
Qiu Ran, Yankai Lin, Peng Li +1
Non-autoregressive neural machine translation (NAT) generates each target word in parallel and has achieved promising inference acceleration. However, existing NAT models still hav…
NumNet: Machine Reading Comprehension with Numerical Reasoning
Qiu Ran, Yankai Lin, Peng Li +2
Numerical reasoning, such as addition, subtraction, sorting and counting is a critical skill in human's reading comprehension, which has not been well considered in existing machin…
Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View
Deli Chen, Yankai Lin, Wei Li +3
Graph Neural Networks (GNNs) have achieved promising performance on a wide range of graph-based tasks. Despite their success, one severe limitation of GNNs is the over-smoothing is…
DocRED: A Large-Scale Document-Level Relation Extraction Dataset
Yuan Yao, Deming Ye, Peng Li +7
Multiple entities in a document generally exhibit complex inter-sentence relations, and cannot be well handled by existing relation extraction (RE) methods that typically focus on…
Fact Discovery from Knowledge Base via Facet Decomposition
Zihao Fu, Yankai Lin, Zhiyuan Liu +1
During the past few decades, knowledge bases (KBs) have experienced rapid growth. Nevertheless, most KBs still suffer from serious incompletion. Researchers proposed many tasks suc…
Graph Neural Networks with Generated Parameters for Relation Extraction
Hao Zhu, Yankai Lin, Zhiyuan Liu +3
Recently, progress has been made towards improving relational reasoning in machine learning field. Among existing models, graph neural networks (GNNs) is one of the most effective…