ACL RD-TEC 1.0 Summarization of P04-2005
Paper Title:
AUTOMATIC ACQUISITION OF ENGLISH TOPIC SIGNATURES BASED ON A SECOND LANGUAGE
AUTOMATIC ACQUISITION OF ENGLISH TOPIC SIGNATURES BASED ON A SECOND LANGUAGE
Primarily assigned technology terms:
- acquisition process
- algorithm
- chinese segmentation
- chinese-english translation
- classification
- clustering
- co-occurrence algorithm
- context-group discrimination
- data collection
- database
- databases
- disambiguation
- disambiguation algorithm
- internet
- internet search
- knowledge acquisition
- knowledge acquisition process
- knowledge bases
- language processing
- learning
- machine learning
- machine translation
- mining
- mobile phone
- natural language processing
- nlp
- pos tagger
- pos tagging
- processing
- querying
- recogniser
- retrieving
- scoring
- search
- search engine
- search engines
- segmentation
- segmentation and pos tagging
- segmenter
- semi-automatic acquisition
- sense classification
- sense disambiguation
- summarisation
- supervised machine learning
- syntactic analysis
- tagger
- tagging
- text segmentation
- text summarisation
- unsupervised disambiguation
- unsupervised method
- word segmenter
- word sense disambiguation
- word space
- word translation
- wsd algorithm
Other assigned terms:
- ambiguity
- ambiguous word
- approach
- baseline performance
- bilingual corpora
- bilingual dictionaries
- bilingual dictionary
- bilingual lexicon
- bilingual lexicons
- bilingual text
- british national corpus
- chinese corpora
- chinese corpus
- chinese gigaword corpus
- chinese language
- chinese text
- chinese translation
- chinese word
- chinese words
- chinese-english lexicon
- cluster
- clusters
- co-occurrence
- concept
- concepts
- content words
- context vector
- context vectors
- context window
- context words
- corpora
- data set
- dictionaries
- dictionary
- document
- english translation
- experimental results
- french
- frequency cut-off
- gold standard
- hand-tagged corpus
- japanese text
- knowledge
- knowledge acquisition bottleneck
- language pair
- language pairs
- lexical knowledge
- lexicon
- linguistic
- linguistic knowledge
- mappings
- maps
- meaning
- meanings
- measure
- method
- monolingual corpora
- natural language
- nlp applications
- nlp tasks
- nouns
- paragraph
- polysemous words
- precision
- process
- queries
- query
- semantic
- semantic similarity
- sense distinctions
- sense granularity
- sense-tagged corpora
- sense-tagged corpus
- senses of a word
- source language
- synonyms
- technique
- technologies
- term
- test data
- text
- tokens
- topic signature
- topics
- training
- training and test data
- training corpus
- training data
- training phase
- translation ambiguity
- translation equivalents
- translation lexicon
- translations
- vector space
- word
- word order
- word sense
- word senses
- word-net
- wordnet
- words
