Dealing with negative samples with multi-task learning on span-based joint entity-relation extraction

by   Chenguang Xue, et al.

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.


page 1

page 2

page 3

page 4


A Two-Phase Paradigm for Joint Entity-Relation Extraction

An exhaustive study has been conducted to investigate span-based models ...

Span-based Joint Entity and Relation Extraction with Transformer Pre-training

We introduce SpERT, an attention model for span-based joint entity and r...

PeerDA: Data Augmentation via Modeling Peer Relation for Span Identification Tasks

Span Identification (SpanID) is a family of NLP tasks that aims to detec...

Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data

In practical scenario, relation extraction needs to first identify entit...

Relation Extraction as Two-way Span-Prediction

The current supervised relation classification (RC) task uses a single e...

A General Framework for Information Extraction using Dynamic Span Graphs

We introduce a general framework for several information extraction task...

HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction

Text-to-Graph extraction aims to automatically extract information graph...

Please sign up or login with your details

Forgot password? Click here to reset