ACL RD-TEC 1.0 Summarization of W00-0801
Paper Title:
AN UNSUPERVISED METHOD FOR MULTILINGUAL WORD SENSE TAGGING USING PARALLEL CORPORA
AN UNSUPERVISED METHOD FOR MULTILINGUAL WORD SENSE TAGGING USING PARALLEL CORPORA
Primarily assigned technology terms:
- algorithm
- bootstrap
- clustering
- corpus alignment
- databases
- disambiguation
- giza
- illustration
- information retrieval
- internet
- knowledge bases
- language understanding
- listing
- machine translation
- machine translation system
- mt system
- mt systems
- natural language understanding
- nlp
- optimization
- preprocessing
- processing
- processing tools
- search
- sense disambiguation
- sense tagging
- similarity calculation
- statistical machine translation
- statistical machine translation system
- tagging
- translation process
- translation selection
- translation system
- translation systems
- translator
- unsupervised method
- viterbi
- viterbi alignment
- word sense tagging
- word translation
- world wide web
Other assigned terms:
- ambiguity
- ambiguous word
- american english
- approach
- bilingual lexicons
- brown corpus
- case
- cluster
- clusters
- co-occurrence
- co-occurrence information
- concept
- concordance
- confidence score
- confidence scores
- context window
- corpora
- cross-linguistic information
- dictionary
- discourse
- distance measure
- domain corpus
- encyclopedia
- english corpus
- english language
- evaluation measure
- evaluation method
- evaluation metric
- evaluation metrics
- fact
- foreign language
- french
- french translation
- french word
- german language
- grammatical relations
- hierarchical structure
- human translation
- implementation
- information content
- knowledge
- knowledge resource
- language corpus
- language information
- language pair
- large corpora
- large corpus
- lexical item
- linguistic
- linguistic knowledge
- linguistic resources
- meaning
- measure
- measures
- method
- multilingual word sense
- natural language
- nlp applications
- noise
- nouns
- ontology
- parallel corpora
- parallel corpus
- part of speech
- part of speech tags
- parts of speech
- penn tree bank
- phrase
- polysemous words
- probability
- process
- punctuation
- punctuation marks
- search space
- selectional preference
- selectional preference information
- semantic
- semantic concordance
- semantic networks
- semcor
- semcor data
- sense ambiguity
- sense distinction
- sense distinctions
- sense inventory
- sentence
- sentence position
- sentences
- slang
- source language
- source language word
- tag set
- tags
- target language
- target language corpus
- target languages
- target sentence
- target word
- taxonomy
- technology
- term
- terms
- test data
- test set
- text
- thesaurus
- tokens
- training
- training material
- translation equivalents
- translation quality
- translations
- tree
- tree bank
- understanding
- verb
- word
- word alignments
- word sense
- word sense ambiguity
- wordnet
- words
