Paper: Subtree Mining for Relation Extraction from Wikipedia

ACL ID N07-2032
Title Subtree Mining for Relation Extraction from Wikipedia
Venue Human Language Technologies
Session Short Paper
Year 2007
Authors

Inthisstudy,weaddresstheproblemofextract- ing relations between entities from Wikipedia’s English articles. Our proposed method first an- chors the appearance of entities in Wikipedia’s articles using neither Named Entity Recognizer (NER) nor coreference resolution tool. It then classifies the relationships between entity pairs using SVM with features extracted from the web structure and subtrees mined from the syntactic structure of text. We evaluate our method on manually annotated data from ac- tual Wikipedia articles.