Paper: A Rote Extractor With Edit Distance-Based Generalisation And Multi-Corpora Precision Calculation

ACL ID P06-2002
Title A Rote Extractor With Edit Distance-Based Generalisation And Multi-Corpora Precision Calculation
Venue Annual Meeting of the Association of Computational Linguistics
Session Poster Session
Year 2006
Authors

In this paper, we describe a rote extrac- tor that learns patterns for finding seman- tic relationships in unrestricted text, with new procedures for pattern generalization and scoring. These include the use of part- of-speech tags to guide the generalization, Named Entity categories inside the pat- terns, an edit-distance-based pattern gen- eralization algorithm, and a pattern accu- racy calculation procedure based on eval- uating the patterns on several test corpora. In an evaluation with 14 entities, the sys- temattainsaprecisionhigherthan50%for half of the relationships considered.