2009 UncertaintyDetectionForIE

• (Goujon, 2009) ⇒ Bénédicte Goujon. (2009). “Uncertainty Detection For Information Extraction.” In: Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2009)

http://lml.bas.bg/ranlp2009/

Subject Headings:

Quotes

Author Keywords

• Semantic Annotation, Information Extraction, Event Extraction, Uncertainty, Linguistic Patterns.

Abstract

• The detection of factual information from texts, like relations or events, is an important task in natural language processing. However most of the tools dealing with information extraction do not take into account the nuances expressed by the author, such as uncertainty. In those applications, the sentence "According to a witness, Y has met X" is reduced to its second part. The lost of the uncertainty expressed by the use of the secondary source "a witness" transforms the understanding of the whole information. The method presented in this paper aims at detecting the uncertainty and the reality of the information described in texts, and captures whether an information is presented as past, with a moderate uncertainty or in a negative way. The method is implemented in a web service for event annotation from texts, which is used in strategic watch applications.

---

,

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2009 UncertaintyDetectionForIE	Bénédicte Goujon			Uncertainty Detection For Information Extraction		Proceedings of the International Conference on Recent Advances in Natural Language Processing	http://www.aclweb.org/anthology-new/R/R09/R09-1023.pdf			2009