Weakly-supervised discovery of named entities using web search queries
Author:
Open Access
- 6 November 2007
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 683-690
Abstract
A seed-based framework for textual information extraction allows for weakly supervised extraction of named entities from anonymized Web search queries. The extraction is guided by a small set of seed named entities, without any need for handcrafted extraction patterns or domain-specific knowledge, allowing for the acquisition of named entities pertaining to various classes of interest to Web search users. Inherently noisy search queries are shown to be a highly valuable, albeit little explored, resource for Web-based named entity discovery.Keywords
This publication has 13 references indexed in Scilit:
- Organizing and searching the world wide web of facts -- step two2007
- Exploring distributional similarity based models for query spelling correction2006
- Weakly supervised named entity transliteration and discovery from multilingual comparable corpora2006
- Mining knowledge from text using information extractionACM SIGKDD Explorations Newsletter, 2005
- KnowItNow2005
- Named entity discovery using comparable news articles2004
- A bootstrapping method for learning semantic lexicons using extraction pattern contexts2002
- Using corpus-derived name lists for named entity recognition2000
- Measures of distributional similarity1999
- A rule-based approach to prepositional phrase attachment disambiguation1994