Semisupervised autoencoder for sentiment analysis
(57) ABSTRACT A method of modelling data, comprising: training an objec tive function of a
linear classifier, based on a set of labeled data, to derive a set of classifier weights; defining …
linear classifier, based on a set of labeled data, to derive a set of classifier weights; defining …
Error reduction in speech processing
JP Lilly, RP Thomas, JP Adams - US Patent 9,697,827, 2017 - Google Patents
BACKGROUND Modern speech recognition systems typically include both speech layer and
understanding layer processing to analyze spoken commands or queries provided by a …
understanding layer processing to analyze spoken commands or queries provided by a …
Machine translation-driven authoring system and method
S Venkatapathy, S Mirkin - US Patent 9,047,274, 2015 - Google Patents
BACKGROUND The exemplary embodiment relates to machine translation and finds
particular application in an authoring system that provides a user interface through which a …
particular application in an authoring system that provides a user interface through which a …
Terminological adaptation of statistical machine translation system through automatic generation of phrasal contexts for bilingual terms
C Servan, M Dymetman - US Patent 9,367,541, 2016 - Google Patents
(57) ABSTRACT A method for terminological adaptation includes receiving a Vocabulary
pair including source and target language terms. Each term is in a class which includes a set …
pair including source and target language terms. Each term is in a class which includes a set …
Lexical and phrasal feature domain adaptation in statistical machine translation
V Nikoulina, S Clinchant - US Patent 9,026,425, 2015 - Google Patents
(57) ABSTRACT A translation method is adapted to a domain of interest. The method
includes receiving a source text string comprising a sequence of source words in a source …
includes receiving a source text string comprising a sequence of source words in a source …
Estimation of parameters for machine translation without in-domain parallel data
P Mathur, S Venkatapathy, N Cancedda - US Patent 9,652,453, 2017 - Google Patents
(57) ABSTRACT A system and method for estimating parameters for features of a translation
scoring function for scoring candidate trans lations in a target domain are provided. Given a …
scoring function for scoring candidate trans lations in a target domain are provided. Given a …
Dynamic bi-phrases for statistical machine translation
A system and a method for phrase-based translation are disclosed. The method includes
receiving source language text to be translated into target language text. One or more …
receiving source language text to be translated into target language text. One or more …
System and method for productive generation of compound words in statistical machine translation
N Cancedda, S Stymne - US Patent 8,781,810, 2014 - Google Patents
(57) ABSTRACT A method and a system for making merging decisions for a translation are
disclosed which are suited to use where the target language is a productive compounding …
disclosed which are suited to use where the target language is a productive compounding …
Insight and algorithmic clustering for automated synthesis
G Swamy - US Patent 9,336,302, 2016 - Google Patents
(52) US Cl. CPC...... G06F 17/3071 (2013.01); G06F 17/30306 (2013.01); G06F 17/30648
(2013.01) A decision Support system and method, which receives user inputs comprising: at …
(2013.01) A decision Support system and method, which receives user inputs comprising: at …
Multi-domain machine translation model adaptation
M Mylonakis, N Cancedda - US Patent 9,235,567, 2016 - Google Patents
A method adapted to multiple corpora includes training a statistical machine translation
model which outputs a score for a candidate translation, in a target language, of a text string …
model which outputs a score for a candidate translation, in a target language, of a text string …