Sciweavers

1360 search results - page 17 / 272
» Risk Analysis with Information Described in Natural Language
Sort
View
GECCO
2003
Springer
100views Optimization» more  GECCO 2003»
15 years 3 months ago
Studying the Advantages of a Messy Evolutionary Algorithm for Natural Language Tagging
The process of labeling each word in a sentence with one of its lexical categories (noun, verb, etc) is called tagging and is a key step in parsing and many other language processi...
Lourdes Araujo
SIGIR
2004
ACM
15 years 3 months ago
Focused named entity recognition using machine learning
In this paper we study the problem of finding most topical named entities among all entities in a document, which we refer to as focused named entity recognition. We show that th...
Li Zhang, Yue Pan, Tong Zhang
ACL
2006
14 years 11 months ago
Minimum Risk Annealing for Training Log-Linear Models
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...
David A. Smith, Jason Eisner
ANLP
1994
105views more  ANLP 1994»
14 years 11 months ago
The Delphi Natural Language Understanding System
This paper presents Delphi, the natural language component of the BBN Spoken Language System. Delphi is a domainindependent natural language question answering system that is soli...
Madeleine Bates, Robert J. Bobrow, Robert Ingria, ...
FP
1995
110views Formal Methods» more  FP 1995»
15 years 1 months ago
Using Types to Parse Natural Language
We describe a natural language parser that uses type information to determine the grammatical structure of simple sentences and phrases. This stands in contrast to studies of type...
Mark P. Jones, Paul Hudak, Sebastian Shaumyan