ACL RD-TEC 1.0 Summarization of C04-1192
Paper Title:
FINE-GRAINED WORD SENSE DISAMBIGUATION BASED ON PARALLEL CORPORA, WORD ALIGNMENT, WORD CLUSTERING AND ALIGNED WORDNETS
FINE-GRAINED WORD SENSE DISAMBIGUATION BASED ON PARALLEL CORPORA, WORD ALIGNMENT, WORD CLUSTERING AND ALIGNED WORDNETS
Authors: Dan Tufis and Radu Ion and Nancy Ide
Primarily assigned technology terms:
- agglomerative clustering
- algorithm
- alignment algorithm
- automatic extraction
- bootstrap
- clustering
- clustering algorithm
- clustering method
- computational linguistics
- context identification and characterization
- disambiguation
- error-correction
- hierarchical clustering
- hypothesis testing
- identification
- language processing
- language translation
- lexical alignment
- linking
- majority voting
- natural language processing
- processing
- sense clustering
- sense disambiguation
- sentence alignment
- supervised training
- tokenizer
- translator
- translators
- validation
- voting
- word alignment
- word alignment algorithm
- word clustering
- word sense disambiguation
- world wide web
- wsd algorithm
Other assigned terms:
- alignment problem
- ambiguity
- ambiguous word
- annotation
- annotators
- approach
- backoff
- bag of words
- baseline clustering
- bitext
- case
- checker
- cluster
- clusters
- concept
- concepts
- context information
- context words
- corpora
- cross-lingual ambiguity
- dictionaries
- dictionary
- dictionary entry
- f-measure
- formalization
- french
- gold standard
- grammatical relations
- heuristic
- heuristics
- human annotators
- hypothesis
- index
- knowledge
- labeling
- language resources
- lexical items
- linguistics
- meanings
- measure
- measures
- method
- multiword expressions
- natural language
- nouns
- ordered list
- parallel corpora
- parallel corpus
- parallel text
- parallel texts
- part of speech
- polysemous words
- precision
- princeton wordnet
- priori
- procedure
- quality assurance
- romanian wordnet
- semantic
- semantic similarity
- sense inventory
- senses of a word
- sentence
- sentences
- serbian
- similarity measures
- similarity score
- source language
- stem
- subjectivity
- subtrees
- synsets
- target language
- target word
- terms
- text
- training
- training data
- transitivity
- translation dictionary
- translation equivalence
- translation equivalent
- translation equivalents
- translation pairs
- translations
- tree
- word
- word sense
- wordnet
- words
- wsd annotation
