Distant Supervision for Relation Extraction with Matrix Completion

2014 ◽  
Author(s):  
Miao Fan ◽  
Deli Zhao ◽  
Qiang Zhou ◽  
Zhiyuan Liu ◽  
Thomas Fang Zheng ◽  
...  
Keyword(s):  
Matrix Completion ◽  
Relation Extraction ◽  
Distant Supervision

Bootstrapped Multi-level Distant Supervision for Relation Extraction

2018 ◽  
pp. 408-423 ◽  
Author(s):  
Ying He ◽  
Zhixu Li ◽  
Guanfeng Liu ◽  
Fangfei Cao ◽  
Zhigang Chen ◽  
...  
Keyword(s):  
Relation Extraction ◽  
Distant Supervision ◽  
Multi Level

scholarly journals Chemical-induced disease relation extraction via attention-based distant supervision

2019 ◽  
Vol 20 (1) ◽  
Author(s):  
Jinghang Gu ◽  
Fuqing Sun ◽  
Longhua Qian ◽  
Guodong Zhou
Keyword(s):  
Relation Extraction ◽  
Distant Supervision

scholarly journals Self-Attention Enhanced Selective Gate with Entity-Aware Embedding for Distantly Supervised Relation Extraction

2020 ◽  
Vol 34 (05) ◽  
pp. 8269-8276
Author(s):  
Yang Li ◽  
Guodong Long ◽  
Tao Shen ◽  
Tianyi Zhou ◽  
Lina Yao ◽  
...  
Keyword(s):  
Selective Attention ◽  
Relation Extraction ◽  
Attention Mechanism ◽  
Position Information ◽  
Distant Supervision ◽  
Gating Mechanism ◽  
The Rich ◽  
Training Examples ◽  
Relation Classification ◽  
Relative Position Information

Distantly supervised relation extraction intrinsically suffers from noisy labels due to the strong assumption of distant supervision. Most prior works adopt a selective attention mechanism over sentences in a bag to denoise from wrongly labeled data, which however could be incompetent when there is only one sentence in a bag. In this paper, we propose a brand-new light-weight neural framework to address the distantly supervised relation extraction problem and alleviate the defects in previous selective attention framework. Specifically, in the proposed framework, 1) we use an entity-aware word embedding method to integrate both relative position information and head/tail entity embeddings, aiming to highlight the essence of entities for this task; 2) we develop a self-attention mechanism to capture the rich contextual dependencies as a complement for local dependencies captured by piecewise CNN; and 3) instead of using selective attention, we design a pooling-equipped gate, which is based on rich contextual representations, as an aggregator to generate bag-level representation for final relation classification. Compared to selective attention, one major advantage of the proposed gating mechanism is that, it performs stably and promisingly even if only one sentence appears in a bag and thus keeps the consistency across all training examples. The experiments on NYT dataset demonstrate that our approach achieves a new state-of-the-art performance in terms of both AUC and top-n precision metrics.

scholarly journals Improving Distantly Supervised Relation Extraction with Neural Noise Converter and Conditional Optimal Selector

2019 ◽  
Vol 33 ◽  
pp. 7273-7280 ◽  
Author(s):  
Shanchan Wu ◽  
Kai Fan ◽  
Qiong Zhang
Keyword(s):  
Transition Matrix ◽  
Noisy Data ◽  
Relation Extraction ◽  
The Other ◽  
Neural Noise ◽  
Distant Supervision ◽  
Other Hand ◽  
The Impact ◽  
Large Corpus

Distant supervised relation extraction has been successfully applied to large corpus with thousands of relations. However, the inevitable wrong labeling problem by distant supervision will hurt the performance of relation extraction. In this paper, we propose a method with neural noise converter to alleviate the impact of noisy data, and a conditional optimal selector to make proper prediction. Our noise converter learns the structured transition matrix on logit level and captures the property of distant supervised relation extraction dataset. The conditional optimal selector on the other hand helps to make proper prediction decision of an entity pair even if the group of sentences is overwhelmed by no-relation sentences. We conduct experiments on a widely used dataset and the results show significant improvement over competitive baseline methods.

Relation Extraction Using Distant Supervision

2019 ◽  
Vol 51 (5) ◽  
pp. 1-35 ◽  
Author(s):  
Alisa Smirnova ◽  
Philippe Cudré-Mauroux
Keyword(s):  
Relation Extraction ◽  
Distant Supervision
Sign in / Sign up

Export Citation Format

Share Document