Adaptive Natural Language Processing
Abstract
A handful of special purpose systems have been successfully deployed to extract prespecified kinds of data from text. The limitation to widespread deployment of such systems is their assumption of a large volume of handcrafted, domain-dependent, and language-dependent knowledge in the form of rules. A new approach is to add automatically trainable probabilistic language models to linguistically based analysis. This offers several potential advantages: (1) Trainability by finding patterns in a large corpus, rather than handcrafting such patterns. (2) Improvability be re-estimating probabilities based on a user marking correct and incorrect output on a test set. (3) More accurate selection among interpretations when more than one is produced. (4) Robustness by finding the most likely partial interpretation when no complete interpretation can be found.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 1991
- Accession Number
- ADA241336
Entities
People
- Damaris Ayuso
- Herbert Gish
- Robert Bobrow
- Robert Ingria
- Sean Boisen
Organizations
- BBN Technologies