Best from Top k Versus Top 1: Improving Distant Supervision Relation Extraction with Deep Reinforcement Learning

We present a novel approach to improve the performance of distant supervision relation extraction with Positive and Unlabeled (PU) Learning. This approach first applies reinforcement learning to decide whether a sentence is positive to a given relation, and then positive and unlabeled bags are constructed. In contrast to most previous studies, which mainly use selected positive instances only, we make full use of unlabeled instances and propose two new representations for positive and unlabeled bags. These two representations are then combined in an appropriate way to make bag-level prediction. Experimental results on a widely used real-world dataset demonstrate that this new approach indeed achieves significant and consistent improvements as compared to several competitive baselines.

Download Full-text

A Hierarchical Framework for Relation Extraction with Reinforcement Learning

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33017072 ◽

2019 ◽

Vol 33 ◽

pp. 7072-7079 ◽

Cited By ~ 10

Author(s):

Ryuichi Takanobu ◽

Tianyang Zhang ◽

Jiexi Liu ◽

Minlie Huang

Keyword(s):

Reinforcement Learning ◽

Relation Extraction ◽

Extraction Process ◽

Entity Extraction ◽

Hierarchical Framework ◽

Hierarchical Reinforcement Learning ◽

Distant Supervision ◽

Public Datasets ◽

Determine Relation

Most existing methods determine relation types only after all the entities have been recognized, thus the interaction between relation types and entity mentions is not fully modeled. This paper presents a novel paradigm to deal with relation extraction by regarding the related entities as the arguments of a relation. We apply a hierarchical reinforcement learning (HRL) framework in this paradigm to enhance the interaction between entity mentions and relation types. The whole extraction process is decomposed into a hierarchy of two-level RL policies for relation detection and entity extraction respectively, so that it is more feasible and natural to deal with overlapping relations. Our model was evaluated on public datasets collected via distant supervision, and results show that it gains better performance than existing methods and is more powerful for extracting overlapping relations1.

Download Full-text

Distant Supervision Relation Extraction via Reinforcement Learning with Potential Energy Function

10.1145/3494885.3494896 ◽

2021 ◽

Author(s):

Tao Zhang ◽

Jun Feng ◽

Jiamin Lu

Keyword(s):

Reinforcement Learning ◽

Potential Energy ◽

Energy Function ◽

Relation Extraction ◽

Potential Energy Function ◽

Distant Supervision

Download Full-text

Joint Entity and Relation Extraction with a Hybrid Transformer and Reinforcement Learning Based Model

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i05.6471 ◽

2020 ◽

Vol 34 (05) ◽

pp. 9314-9321

Author(s):

Ya Xiao ◽

Chengxiang Tan ◽

Zhijie Fan ◽

Qian Xu ◽

Wenye Zhu

Keyword(s):

Reinforcement Learning ◽

Noisy Data ◽

Relation Extraction ◽

Input State ◽

Data Filtering ◽

The Public ◽

Distant Supervision ◽

Proposed Model ◽

Public Dataset ◽

Relation Classification

Joint extraction of entities and relations is a task that extracts the entity mentions and semantic relations between entities from the unstructured texts with one single model. Existing entity and relation extraction datasets usually rely on distant supervision methods which cannot identify the corresponding relations between a relation and the sentence, thus suffers from noisy labeling problem. We propose a hybrid deep neural network model to jointly extract the entities and relations, and the model is also capable of filtering noisy data. The hybrid model contains a transformer-based encoding layer, an LSTM entity detection module and a reinforcement learning-based relation classification module. The output of the transformer encoder and the entity embedding generated from the entity detection module are combined as the input state of the reinforcement learning module to improve the relation classification and noisy data filtering. We conduct experiments on the public dataset produced by the distant supervision method to verify the effectiveness of our proposed model. Different experimental results show that our model gains better performance on entity and relation extraction than the compared methods and also has the ability to filter noisy sentences.

Download Full-text