Abstract
Joint named entity recognition and relation extraction is an essential natural language processing task that aims to identify entities and extract the corresponding relations in an end-to-end manner. At present, compared with the named entity recognition task, the relation extraction task performs poorly on complex text. To solve this problem, we proposed a novel joint model named extracting Entity-Relations viaImproved Graph Attention networks (ERIGAT), which enhances the ability of the relation extraction task. In our proposed model, we introduced the graph attention network to extract entities and relations after graph embedding based on constructing symmetry relations. To mitigate the over-smoothing problem of graph convolutional networks, inspired by matrix factorization, we improved the graph attention network by designing a new multi-head attention mechanism and sharing attention parameters. To enhance the model robustness, we adopted the adversarial training to generate adversarial samples for training by adding tiny perturbations. Comparing with typical baseline models, we comprehensively evaluated our model by conducting experiments on an open domain dataset (CoNLL04) and a medical domain dataset (ADE). The experimental results demonstrate the effectiveness of ERIGAT in extracting entity and relation information.
Highlights
It is challenging to perform joint named entity recognition (NER) and relation extraction (RE) from unstructured text is in the natural language processing (NLP) and information extraction domains.As an example, given the sentence in Figure 1, the process uses different tags to mark entities and relations during the NER and RE tasks
We applied our Entity-Relations viaImproved Graph Attention networks (ERIGAT) method to an open domain dataset (CoNLL04) and a medical domain dataset (ADE), and we evaluated the results with the previously proposed baseline models to verify the validity of ERIGAT
ERIGAT-No Ad (CoNLL04 is 79.81% and ADE is 83.77%), which reflects that increasing the robustness of the model by adversarial training can improve the performance of the ERIGAT model
Summary
It is challenging to perform joint named entity recognition (NER) and relation extraction (RE) from unstructured text is in the natural language processing (NLP) and information extraction domains.As an example, given the sentence in Figure 1, the process uses different tags to mark entities and relations during the NER and RE tasks. Given the sentence, the process uses different tags to mark entities and relations during the NER and RE tasks. In this example, Harrington (Peop), Harvard University (Org), and National War College (Org) are three entities: the entity type of Harrington is a “person,” and the entity type of Harvard University or National War College (Org) is an “organization.” The phrase “Work_for” denotes the relation type between Harrington (Peop) and Harvard University (Org) or National War College (Org), respectively. In contrast to the pipeline model, the joint model treats NER and RE as two interrelated tasks that do not have a strict upstream and downstream relationship
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.