Multi-Task Transfer Learning for Weakly-Supervised Relation Extraction
Creating labeled training data for relation extraction is expensive. In this paper, we study relation extraction in a special weakly-supervised setting when we have only a few seed instances of the target relation type we want to extract but we also have a large amount of labeled instances of other...
Saved in:
| 主要作者: | |
|---|---|
| 格式: | text |
| 語言: | English |
| 出版: |
Institutional Knowledge at Singapore Management University
2009
|
| 主題: | |
| 在線閱讀: | https://ink.library.smu.edu.sg/sis_research/352 https://ink.library.smu.edu.sg/context/sis_research/article/1351/viewcontent/P09_1114.pdf |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 機構: | Singapore Management University |
| 語言: | English |
| 總結: | Creating labeled training data for relation extraction is expensive. In this paper, we study relation extraction in a special weakly-supervised setting when we have only a few seed instances of the target relation type we want to extract but we also have a large amount of labeled instances of other relation types. Observing that different relation types can share certain common structures, we propose to use a multi-task learning method coupled with human guidance to address this weakly-supervised relation extraction problem. The proposed framework models the commonality among different relation types through a shared weight vector, enables knowledge learned from the auxiliary relation types to be transferred to the target relation type, and allows easy control of the tradeoff between precision and recall. Empirical evaluation on the ACE 2004 data set shows that the proposed method substantially improves over two baseline methods. |
|---|