Relation adaptation: Learning to extract novel relations with minimum supervision

Danushka Bollegala, Yutaka Matsuo, Mitsuru Ishizuka

研究成果: Conference contribution

13 被引用数 (Scopus)

抄録

Extracting the relations that exist between two entities is an important step in numerous Web-related tasks such as information extraction. A supervised relation extraction system that is trained to extract a particular relation type might not accurately extract a new type of a relation for which it has not been trained. However, it is costly to create training data manually for every new relation type that one might want to extract. We propose a method to adapt an existing relation extraction system to extract new relation types with minimum supervision. Our proposed method comprises two stages: learning a lower-dimensional projection between different relations, and learning a relational classifier for the target relation type with instance sampling. We evaluate the proposed method using a dataset that contains 2000 instances for 20 different relation types. Our experimental results show that the proposed method achieves a statistically significant macro-average F -score of 62.77. Moreover, the proposed method outperforms numerous baselines and a previously proposed weakly-supervised relation extraction method.

本文言語English
ホスト出版物のタイトルIJCAI International Joint Conference on Artificial Intelligence
ページ2205-2210
ページ数6
DOI
出版ステータスPublished - 2011
外部発表はい
イベント22nd International Joint Conference on Artificial Intelligence, IJCAI 2011 - Barcelona, Catalonia
継続期間: 2011 7 162011 7 22

Other

Other22nd International Joint Conference on Artificial Intelligence, IJCAI 2011
CityBarcelona, Catalonia
Period11/7/1611/7/22

ASJC Scopus subject areas

  • Artificial Intelligence

フィンガープリント 「Relation adaptation: Learning to extract novel relations with minimum supervision」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル