@inproceedings{345f7d96756444629c6d24dfca9d6ca4,
title = "Gender and animacy knowledge discovery from web-scale n-grams for unsupervised person mention detection",
abstract = "In this paper we present a simple approach to discover gender and animacy knowledge for person mention detection. We learn noun-gender and noun-animacy pair counts from web-scale n-grams using specific lexical patterns, and then apply confidence estimation metrics to filter noise. The selected informative pairs are then used to detect person mentions from raw texts in an unsupervised learning framework. Experiments showed that this approach can achieve high performance comparable to state-of-the-art supervised learning methods which require manually annotated corpora and gazetteers.",
keywords = "Animacy, Gender, Knowledge discovery, Mention detection, N-grams",
author = "Heng Ji and Dekang Lin",
year = "2009",
language = "English (US)",
isbn = "9789624423198",
series = "PACLIC 23 - Proceedings of the 23rd Pacific Asia Conference on Language, Information and Computation",
pages = "220--229",
booktitle = "PACLIC 23 - Proceedings of the 23rd Pacific Asia Conference on Language, Information and Computation",
note = "23rd Pacific Asia Conference on Language, Information and Computation, PACLIC 23 ; Conference date: 03-12-2009 Through 05-12-2009",
}