ACL RD-TEC 1.0 Summarization of P05-1048
Paper Title:
WORD SENSE DISAMBIGUATION VS. STATISTICAL MACHINE TRANSLATION
WORD SENSE DISAMBIGUATION VS. STATISTICAL MACHINE TRANSLATION
Authors: Marine Carpuat and Dekai Wu
Primarily assigned technology terms:
- adaboost
- algorithm
- bilingual bootstrapping
- boosting
- boosting algorithm
- bootstrapping
- bootstrapping method
- bracketing
- classification
- classifier
- classifiers
- decision trees
- decoder
- decoding
- disambiguation
- entity classification
- error analysis
- full machine translation
- giza
- greedy decoding
- hindi translation disambigation
- information retrieval
- information retrieval systems
- isi rewrite decoder
- kernel
- kpca
- language modeling
- machine translation
- machine translation system
- machine translation systems
- maximum entropy
- maximum entropy model
- maximum-entropy
- model training
- modeling
- mt system
- mt systems
- naive bayes
- named entity classification
- parsing
- part-of-speech tagging
- postprocessing
- preprocessing
- principal component analysis
- reranking
- retrieval systems
- sense annotation
- sense disambiguation
- sentence translation
- smt system
- statistical language modeling
- statistical machine translation
- statistical machine translation system
- statistical mt
- supervised training
- tagging
- translation disambiguation
- translation engine
- translation model training
- translation system
- translation systems
- unsupervised bootstrapping
- voting
- word sense disambiguation
- word translation
- wsd algorithm
Other assigned terms:
- alignment model
- alignment models
- annotated corpus
- annotation
- approach
- bayes model
- bias
- bleu
- bleu metric
- bleu score
- bleu scores
- break
- case
- chinese lexical
- chinese word
- classification model
- classification task
- coherence
- cohesion
- comparable corpora
- comparative study
- context feature
- context features
- contextual features
- contextual information
- corpora
- dictionary
- disambiguation model
- empirical results
- english language
- english language model
- english translation
- english translations
- entropy
- evaluation methodology
- evaluation test
- evaluations
- fact
- feature
- feature set
- feature space
- french
- gold standard
- hindi
- hownet
- hypotheses
- inflected forms
- interpretation
- knowledge
- knowledge base
- language model
- language model probability
- language modeling toolkit
- language models
- language pairs
- lexical choice
- lexical translation
- linguistic
- linguistic information
- local context
- machine translation quality
- manual annotation
- mapping
- mapping model
- maps
- method
- methodology
- model probability
- modeling toolkit
- mt evaluation
- n-gram
- naive bayes model
- named entity
- nist
- parallel corpora
- parallel corpus
- part-of-speech
- predictive information
- preprocessor
- probabilities
- probability
- reference translations
- sense disambiguation model
- sense distinctions
- sense inventory
- sentence
- sentences
- sentential context
- sparse data
- stems
- surface form
- synonyms
- target language
- target sentence
- target word
- terms
- test set
- toolkit
- training
- training corpus
- training data
- training set
- translation candidates
- translation model
- translation models
- translation probabilities
- translation probability
- translation quality
- translation task
- translations
- tree
- trees
- trigram
- trigram model
- word
- word sense
- word type
- wordnet
- wordnet senses
- words
- wsd evaluation
- wsd evaluation methodology
- wsd model
