%0 Conference Proceedings %T Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data %A Ye, Wei %A Li, Bo %A Xie, Rui %A Sheng, Zhonghao %A Chen, Long %A Zhang, Shikun %Y Korhonen, Anna %Y Traum, David %Y Màrquez, Lluís %S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics %D 2019 %8 July %I Association for Computational Linguistics %C Florence, Italy %F ye-etal-2019-exploiting %X 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. %R 10.18653/v1/P19-1130 %U https://aclanthology.org/P19-1130 %U https://doi.org/10.18653/v1/P19-1130 %P 1351-1360