Sciweavers

681 search results - page 92 / 137
» Combining Theorem Proving with Natural Language Processing
Sort
View
IMCSIT
2010
14 years 7 months ago
Generation of First-Order Expressions from a Broad Coverage HPSG Grammar
This paper describes an application for computing first-order semantic representations of English texts. It is based on a combination of hybrid shallow-deep components arranged wit...
Ravi Coote, Andreas Wotzlaw
CICLING
2008
Springer
14 years 11 months ago
Dynamic Translation Memory: Using Statistical Machine Translation to Improve Translation Memory Fuzzy Matches
Abstract. Professional translators of technical documents often use Translation Memory (TM) systems in order to capitalize on the repetitions frequently observed in these documents...
Ergun Biçici, Marc Dymetman
ICASSP
2011
IEEE
14 years 1 months ago
Improved pos tagging for text-to-speech synthesis
One of the fundamental building blocks of text processing for textto-speech (TTS) synthesis is the assignment of a part-of-speech (POS) tag to each input word. POS tags are heavil...
Ming Sun, Jerome R. Bellegarda
WWW
2007
ACM
15 years 10 months ago
Learning information intent via observation
Workers in organizations frequently request help from assistants by sending request messages that express information intent: an intention to update data in an information system....
Anthony Tomasic, Isaac Simmons, John Zimmerman
CORR
2008
Springer
107views Education» more  CORR 2008»
14 years 9 months ago
A Spectral Algorithm for Learning Hidden Markov Models
Hidden Markov Models (HMMs) are one of the most fundamental and widely used statistical tools for modeling discrete time series. In general, learning HMMs from data is computation...
Daniel Hsu, Sham M. Kakade, Tong Zhang