Suwei Wu
ABSTRACT
The extraction of entities and relationships from unstructured text is not only a critical issue in information extraction, but also an essential component of constructing knowledge graphs. Most existing models for relation extraction first extract all subjects, and then proceed to extract objects and relations based on the identified subjects. This method is highly dependent on the extraction of subjects, and the quality of subject extraction significantly impacts the extraction of objects and relations. During relation processing, most models only use the simplest classifier, with the difference lying in the input for relation processing, which sometimes leads to the mutual relationship between the subject and the object being overlooked.To avoid overlooking the inherent features of input sentences, we generate three distinct token representation sequences for subject, object, and relation at the encoding layer. Additionally, combining explicit injection of context features from the encoding layer, entity extraction in both directions can mutually promote each other, aiming to obtain as many entity pairs as possible. This approach aims to address the limitations imposed by the relationship being subject to the extracted subject. While most existing models use a simple classifier for handling relationships, our model employs the Biaffine model combined with an attention mechanism to assign all potential relationships for each entity pair. Its advantage over other simple classifiers is maintaining a matrix for each relation, accurately modeling the features of relations, and its probability calculation mechanism can precisely explore the interaction between subjects and objects.We evaluated the proposed model on the NYT and WebNLG datasets. Extensive experimental results demonstrate the high effectiveness of the proposed model, achieving significant performance across all datasets.
- [1]Li F, Zhang M, Fu G, et al. A Bi-LSTM-RNN model for relation classification using low-cost sequence features[J]. ar**v preprint ar**v:1608.07720, 2016.Google Scholar
- [2]Xu Y, Mou L, Li G, et al. Classifying relations via long short term memory networks along shortest dependency paths[C]//Proceedings of the 2015 conference on empirical methods in natural language processing. 2015: 1785-1794.Google Scholar
- [3]Ren F, Zhang L, Yin S, et al. A novel global feature-oriented relational triple extraction model based on table filling[J]. ar**v preprint ar**v:2109.06705, 2021.Google Scholar
- [4]Wang Y, Sun C, Wu Y, et al. UniRE: A unified label space for entity relation extraction[J]. ar**v preprint ar**v:2107.04292, 2021.Google Scholar
- [5]Dixit K, Al-Onaizan Y. Span-level model for relation extraction[J]. 2019.Google ScholarCross Ref
- [6]Wang Y, Yu B, Zhang Y, et al. TPLinker: Single-stage joint extraction of entities and relations through token pair linking[J]. ar**v preprint ar**v:2010.13415, 2020.Google Scholar
- [7]Wei Z, Su J, Wang Y, et al. A novel cascade binary tagging framework for relational triple extraction[J]. ar**v preprint ar**v:1909.03227, 2019.Google Scholar
- [8]Zheng H, Wen R, Chen X,et al.PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extraction[J]. 2021.DOI:10.18653/v1/2021.acl-long.486.Google ScholarCross Ref
- [9]Ren X, Wu Z, He W, et al. Cotype: Joint extraction of typed entities and relations with knowledge bases[C]//Proceedings of the 26th international conference on world wide web. 2017: 1015-1024.Google Scholar
- [10]Gormley M R, Yu M, Dredze M. Improved relation extraction with feature-rich compositional embedding models[J]. ar**v preprint ar**v:1505.02419, 2015.Google Scholar
- [11]Yu B, Zhang Z, Shu X, et al. Joint extraction of entities and relations based on a novel decomposition strategy[J]. ar**v preprint ar**v:1909.04273, 2019.Google Scholar
- [12]Li X, Yin F, Sun Z, et al. Entity-relation extraction as multi-turn question answering[J]. ar**v preprint ar**v:1905.05529, 2019.Google Scholar
- [13]Zeng X, Zeng D, He S, et al. Extracting relational facts by an end-to-end neural model with copy mechanism[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018: 506-514.Google Scholar
- [14]Devlin J, Chang M W, Lee K, et al. Bert: Pre-training of deep bidirectional transformers for language understanding[J]. ar**v preprint ar**v:1810.04805, 2018.Google Scholar
- [15]Pennington J, Socher R, Manning C D. Glove: Global vectors for word representation[C]//Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP). 2014: 1532-1543.Google Scholar
- [16]Zhong P, Wang D, Miao C. Knowledge-enriched transformer for emotion detection in textual conversations[J]. ar**v preprint ar**v:1909.10681, 2019.Google Scholar
- [17]Sun K, Zhang R, Mensah S, et al. Progressive multi-task learning with controlled information flow for joint entity and relation extraction[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2021, 35(15): 13851-13859.Google ScholarCross Ref
- [18]Yu J, Bohnet B, Poesio M. Named entity recognition as dependency parsing[J]. ar**v preprint ar**v:2005.07150, 2020.Google Scholar
- [19]Riedel S, Yao L, McCallum A. Modeling relations and their mentions without labeled text[C]//Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2010, Barcelona, Spain, September 20-24, 2010, Proceedings, Part III 21. Springer Berlin Heidelberg, 2010: 148-163.Google Scholar
- [20]Gardent C, Shimorina A, Narayan S, et al. Creating training corpora for nlg micro-planning[C]//55th annual meeting of the Association for Computational Linguistics (ACL). 2017.Google Scholar
Index Terms
- Entity relation extraction based on Biaffine model with embedded context features
Recommendations
An entity relation extraction method based on the fusion of contextual information
CNIOT '23: Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of ThingsWith the growth of information technology, numerous entity relation extraction methods have developed. However, current studies primarily emphasize effective entity recognition, disregarding the significance of local information about entities in text ...
Research on multi-feature fusion entity relation extraction based on deep learning
Entity relation extraction aims to identify the semantic relation category between the target entity pairs in the original text and is one of the core technologies of tasks such as automatic document summarisation, automatic question answering system, and ...
Review of entity relation extraction
In today’s big data era, there are a large number of unstructured information resources on the web. Natural language processing researchers have been working hard to figure out how to extract useful information from them. Entity Relation Extraction is a ...
Comments