Proper Name Extraction from Non-Journalistic Texts

Published 1 January 2001

Thierry Poibeau, Leila Kosseim

Citations84

TL;DR

The influence of the corpus on the automatic identification of proper names in texts is discussed and an approach to adapt a proper name extraction system developed for newspapers to the analysis of e-mail is described.

Abstract

In this paper, the syntactic properties of parenthetical reporting clauses in Dutch are investigated by means of a small corpus. It is shown that an analysis in which the quote is looked upon as the direct object of the reporting verb is inadequate. Therefore, an alternative analysis is proposed, viz. one in which the quote and the reporting clause are taken to be adjoined. Such an analysis, however, is not unproblematic. Here we discuss the two main problems with this analysis.

Keywords

Computer Science

International Joint Conference on Artificial IntelligenceFASTUS: A Finite-state Processor for Information Extraction from Real-world Text.

256 Citations1993Douglas E. Appelt, Jerry R. Hobbs +3 more

FASTUS has been evaluated on several blind tests that demonstrate that state-of-the-art performance on information-extraction tasks is obtainable with surprisingly little computational effort.

Terminology International Journal of Theoretical and Applied Issues in Specialized CommunicationEmpirical observation of term variations and principles for their description

170 Citations1996Béatrice Daille, Benoît Habert +2 more

A precise linguistic description of the rules relating to controlled terms and observed variants and of the constraints on these rules is given, which leads to novel means of enriching terminologies via the generation of possible term variants or the simplification of nominal parse trees in order to discover potential variants.

MITRE

126 Citations1995John Aberdeen, John D. Burger +4 more

As with several other veteran MUC participants, MITRE's Alembic system has undergone a major transformation in the past two years.

View PDF

Language in SocietyThe context of oral and written language: A framework for mode and medium switching

115 Citations1988Denise E. Murray

A framework is proposed that suggests an integrated approach for examining oral and written language, an approach grounded in the view that literacy and orality are social practices whose forms and functions vary for different social groups.

Prelexical locus of an illusory vowel effect in Japanese

60 Citations1999Emmanuel Dupoux, Takao Fushimi +2 more

In experiments on the Broadcast News corpus, it is found that prosodic cues alone allow sentence and topic segmentation that is at least as good as word-based methods alone, and that combining both types of cues gives significant wins.

Using Collocation Statistics in Information Extraction

45 Citations1998Dekang Lin

The main objective in participating MUC-7 is to investigate and experiment with the use of collocation statistics in information extraction, which refers to the frequency counts of the collocational relations extracted from a parsed corpus.

Locating noun phrases with finite state transducers

10 Citations1998Jean Sénellart

A method for constructing, maintaining and consulting a database of proper nouns and shows how it can handle requests such as: 'Find all newspaper articles in a general corpus mentioning the French prime minister', or 'How is Mr. X referred to in the corpus; what have been his different occupations through out the period over which the authors' corpus extends?'

View PDF