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

arXiv: https://arxiv.org/abs/1906.08931 · HTML: https://mlsanity.com/paper/1906.08931/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jun 2019.

## Built on by (most cited first, 11 of 11)

- [Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness](https://mlsanity.com/paper/2304.11633/) (2023)
- [Multi-Task Learning in Natural Language Processing: An Overview](https://mlsanity.com/paper/2109.09138/) (2021)
- [What do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classification](https://mlsanity.com/paper/2204.13516/) (2022)
- [Reviewing Labels: Label Graph Network with Top-k Prediction Set for Relation Extraction](https://mlsanity.com/paper/2212.14270/) (2022)
- [Sequence Generation with Label Augmentation for Relation Extraction](https://mlsanity.com/paper/2212.14266/) (2022)
- [Multi-view Inference for Relation Extraction with Uncertain Knowledge](https://mlsanity.com/paper/2104.13579/) (2021)
- [Span-based joint entity and relation extraction augmented with sequence tagging mechanism](https://mlsanity.com/paper/2210.12720/) (2022)
- [Enriched Attention for Robust Relation Extraction](https://mlsanity.com/paper/2104.10899/) (2021)
- [Boosting Span-based Joint Entity and Relation Extraction via Squence Tagging Mechanism](https://mlsanity.com/paper/2105.10080/) (2021)
- [Tackling Multiple Tasks with One Single Learning Framework](https://mlsanity.com/paper/2206.06322/) (2022)
- [A Two-Phase Paradigm for Joint Entity-Relation Extraction](https://mlsanity.com/paper/2208.08659/) (2022)

## Abstract (arXiv)

In practical scenario, relation extraction needs to first identify entity pairs that have relation and then assign a correct relation class. However, the number of non-relation entity pairs in context (negative instances) usually far exceeds the others (positive instances), which negatively affects a model's performance. To mitigate this problem, we propose a multi-task architecture which jointly trains a model to perform relation identification with cross-entropy loss and relation classification with ranking loss. Meanwhile, we observe that a sentence may have multiple entities and relation mentions, and the patterns in which the entities appear in a sentence may contain useful semantic information that can be utilized to distinguish between positive and negative instances. Thus we further incorporate the embeddings of character-wise/word-wise BIO tag from the named entity recognition task into character/word embeddings to enrich the input representation. Experiment results show that our proposed approach can significantly improve the performance of a baseline model with more than 10% absolute increase in F1-score, and outperform the state-of-the-art models on ACE 2005 Chinese and English corpus. Moreover, BIO tag embeddings are particularly effective and can be used to improve other models as well.