Incorporating Boundary and Category Feature for Nested Named Entity Recognition

Cao, Jin; Wang, Guohua; Li, Canguang; Ren, Haopeng; Cai, Yi; Wong, Raymond Chi-Wing; Li, Qing

doi:10.1007/978-3-030-59416-9_13

Cited by 3 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, numerous experiments have employed multi-task learning methods to train NER and RE models. Zheng et al [15], Cao et al [16], and Tan et al [17] used multi-task learning to capture the dependencies between entity boundaries and their classification labels. Fei et al [18] proposed treating each unique entity type as a separate task to facilitate information exchange between biomedical NER tasks using multi-task learning.…”

Section: Introductionmentioning

confidence: 99%

Dealing with Negative Samples with Multi-Task Learning on Span-Based Joint Entity-Relation Extraction

Lu,

Xue

2023

Machine Learning Techniques and NLP

View full text Add to dashboard Cite

Recent span-based joint extraction models have demonstrated significant advantages in both entity recognition and relation extraction. These models treat text spans as candidate entities, and span pairs as candidate relationship tuples, achieving state-of-the-art results on datasets like ADE. However, these models encounter a significant number of non-entity spans or irrelevant span pairs during the tasks, impairing model performance significantly. To address this issue, this paper introduces a span-based multitask entity-relation joint extraction model. This approach employs the multitask learning to alleviate the impact of negative samples on entity and relation classifiers. Additionally, we leverage the Intersection over Union(IoU) concept to introduce the positional information into the entity classifier, achieving a span boundary detection. Furthermore, by incorporating the entity Logits predicted by the entity classifier into the embedded representation of entity pairs, the semantic input for the relation classifier is enriched. Experimental results demonstrate that our proposed SpERT.MT model can effectively mitigate the adverse effects of excessive negative samples on the model performance. Furthermore, the model demonstrated commendable F1 scores of 73.61%, 53.72%, and 83.72% on three widely employed public datasets, namely CoNLL04, SciERC, and ADE, respectively.

show abstract