PARE: A Simple and Strong Baseline for Monolingual and Multilingual Distantly Supervised Relation Extraction

PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022): (SHORT PAPERS), VOL 2(2022)

引用 9|浏览63
暂无评分
摘要
Neural models for distantly supervised relation extraction (DS-RE) encode each sentence in an entity-pair bag separately. These are then aggregated for bag-level relation prediction. Since, at encoding time, these approaches do not allow information to flow from other sentences in the bag, we believe that they do not utilize the available bag data to the fullest. In response, we explore a simple baseline approach (PARE) in which all sentences of a bag are concatenated into a passage of sentences, and encoded jointly using BERT. The contextual embeddings of tokens are aggregated using attention with the candidate relation as query - this summary of whole passage predicts the candidate relation. We find that our simple baseline solution outperforms existing state-of-the-art DS-RE models in both monolingual and multilingual DS-RE datasets.
更多
查看译文
关键词
distantly supervised relation extraction,multilingual
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要