• Publications
  • Influence
Learning Entity and Relation Embeddings for Knowledge Graph Completion
TLDR
TransR is proposed to build entity and relation embeddings in separate entity space and relation spaces to build translations between projected entities and to evaluate the models on three tasks including link prediction, triple classification and relational fact extraction. Expand
Neural Relation Extraction with Selective Attention over Instances
TLDR
A sentence-level attention-based model for relation extraction that employs convolutional neural networks to embed the semantics of sentences and dynamically reduce the weights of those noisy instances. Expand
Modeling Relation Paths for Representation Learning of Knowledge Bases
TLDR
This model considers relation paths as translations between entities for representation learning, and addresses two key challenges: (1) Since not all relation paths are reliable, it design a path-constraint resource allocation algorithm to measure the reliability of relation paths and (2) represents relation paths via semantic composition of relation embeddings. Expand
DocRED: A Large-Scale Document-Level Relation Extraction Dataset
TLDR
Empirical results show that DocRED is challenging for existing RE methods, which indicates that document-level RE remains an open problem and requires further efforts. Expand
Neural Sentiment Classification with User and Product Attention
TLDR
A hierarchical neural network is proposed to incorporate global user and product information into sentiment classification and achieves significant and consistent improvements compared to all state-of-theart methods. Expand
Denoising Distantly Supervised Open-Domain Question Answering
TLDR
A novel DS-QA model which employs a paragraph selector to filter out those noisy paragraphs and a paragraph reader to extract the correct answer from those denoised paragraphs is proposed which can capture useful information from noisy data and achieve significant improvements on DS- QA as compared to all baselines. Expand
Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View
TLDR
Two methods to alleviate the over-smoothing issue of GNNs are proposed: MADReg which adds a MADGap-based regularizer to the training objective and AdaGraph which optimizes the graph topology based on the model predictions. Expand
OpenKE: An Open Toolkit for Knowledge Embedding
TLDR
An open toolkit for knowledge embedding, which provides a unified framework and various fundamental models to embed knowledge graphs into a continuous low-dimensional space and the embeddings of some existing large-scale knowledge graphs pre-trained by OpenKE are available. Expand
NumNet: Machine Reading Comprehension with Numerical Reasoning
TLDR
A numerical MRC model named as NumNet is proposed, which utilizes a numerically-aware graph neural network to consider the comparing information and performs numerical reasoning over numbers in the question and passage, outperforming all existing machine reading comprehension models by considering the numerical relations among numbers. Expand
XQA: A Cross-lingual Open-domain Question Answering Dataset
TLDR
A novel dataset XQA is constructed that consists of a training set in English as well as development and test sets in eight other languages and provides several baseline systems for cross-lingual OpenQA, showing that the multilingual BERT model achieves the best results in almost all target languages. Expand
...
1
2
3
4
5
...