ACL RD-TEC 1.0 Summarization of W02-1012
Paper Title:
EXTENTIONS TO HMM-BASED STATISTICAL WORD ALIGNMENT MODELS
EXTENTIONS TO HMM-BASED STATISTICAL WORD ALIGNMENT MODELS
Authors: Kristina Toutanova and H. Tolga Ilhan and Christopher Manning
Primarily assigned technology terms:
- algorithm
- approximation
- chinese language modeling
- classification
- computational linguistics
- decomposition
- delta function
- dynamic programming
- dynamic programming algorithm
- error reduction
- forward-backward algorithm
- giza
- hidden markov
- induction
- language modeling
- language processing
- language translation
- learning
- learning algorithms
- linear interpolation
- localization
- machine translation
- markov alignment model
- markov model
- modeling
- natural language translation
- noisy channel model
- part-of-speech tagging
- processing
- programming algorithm
- smoothing
- statistical machine translation
- statistical translation
- statistical word alignment
- taggers
- tagging
- terminology
- translation modeling
- tuning
- validation
- viterbi
- word alignment
- word translation
Other assigned terms:
- adjective
- alignment accuracy
- alignment error rate
- alignment model
- alignment models
- alignment probability
- approach
- association for computational linguistics
- baseline model
- bigram
- bilingual corpora
- case
- chinese language
- cluster
- corpora
- data set
- data sets
- determiner
- distribution
- english sentence
- error rate
- estimation
- evaluation metric
- experimental results
- french
- french sentence
- french word
- function words
- generation
- generation model
- generative model
- hmm model
- hmm-based model
- ibm model
- ibm models
- index
- interpolation
- joint probability
- knowledge
- language model
- language pairs
- large corpora
- linguistics
- mapping
- maps
- markov models
- method
- model parameters
- natural language
- noisy channel
- noun phrase
- order variation
- parallel corpora
- parallel text
- part of speech
- part of speech tags
- part-of-speech
- parts of speech
- permutation
- phrase
- pos tag
- pos tag information
- prior distribution
- probabilities
- probability
- probability distribution
- punctuation
- sentence
- sentences
- set size
- source language
- source sentence
- sparse data
- speech information
- speech tag
- statistical translation model
- stem
- syntactic knowledge
- tag information
- tag sequence
- tag set
- tags
- target language
- target language sentence
- target language string
- target languages
- target sentence
- target word
- test data
- test set
- text
- training
- training corpora
- training corpus
- training data
- training set
- training set size
- translation model
- translation models
- translation probabilities
- translation probability
- translations
- uniform distribution
- verb
- word
- word alignment accuracy
- word classes
- word level
- word level alignment
- word order
- word order variation
- word types
- words
