Sciweavers

NAACL
2001
13 years 5 months ago
Generating Training Data for Medical Dictations
In automatic speech recognition (ASR) enabled applications for medical dictations, corpora of literal transcriptions of speech are critical for training both speaker independent a...
Sergey V. Pakhomov, Michael Schonwetter, Joan Bach...
NAACL
2001
13 years 5 months ago
Information-Based Machine Translation
This paper describes an approach to Machine Translation that places linguistic information at its foundation. The difficulty of translation from English to Japanese is illustrated...
Keiko Horiguchi
NAACL
2001
13 years 5 months ago
Edit Detection and Parsing for Transcribed Speech
We present a simple architecture for parsing transcribed speech in which an edited-word detector first removes such words from the sentence string, and then a standard statistical...
Eugene Charniak, Mark Johnson
NAACL
2001
13 years 5 months ago
Unsupervised Learning of Name Structure From Coreference Data
We present two methods for learning the structure of personal names from unlabeled data. The first simply uses a few implicit constraints governing this structure to gain a toehol...
Eugene Charniak
NAACL
2001
13 years 5 months ago
Learning Optimal Dialogue Management Rules by Using Reinforcement Learning and Inductive Logic Programming
Developing dialogue systems is a complex process. In particular, designing efficient dialogue management strategies is often difficult as there are no precise guidelines to develo...
Renaud Lecoeuche
NAACL
2001
13 years 5 months ago
A Corpus-based Account of Regular Polysemy: The Case of Context-sensitive Adjectives
In this paper we investigate polysemous adjectives whose meaning varies depending on the nouns they modify (e.g., fast). We acquire the meanings of these adjectives from a large c...
Maria Lapata
NAACL
2001
13 years 5 months ago
Chunking with Support Vector Machines
We apply Support Vector Machines (SVMs) to identify English base phrases (chunks). SVMs are known to achieve high generalization performance even with input data of high dimension...
Taku Kudo, Yuji Matsumoto