ACL RD-TEC 1.0 Summarization of W06-1620
Paper Title:
MULTILINGUAL DEEP LEXICAL ACQUISITION FOR HPSGS VIA SUPERTAGGING
MULTILINGUAL DEEP LEXICAL ACQUISITION FOR HPSGS VIA SUPERTAGGING
Authors: Phil Blunsom and Timothy Baldwin
Primarily assigned technology terms:
- algorithm
- approximation
- beam search
- computational linguistics
- crfs
- decoding
- deep lexical acquisition
- dla
- encoding
- english pos tagger
- feature engineering
- finite state
- finite state machine
- identification
- incremental learning
- language processing
- learner
- learning
- learning approach
- learning process
- lemmatisation
- lexical acquisition
- likelihood estimation
- maximum likelihood
- maximum likelihood estimation
- morphological processing
- morphology
- natural language processing
- numerical optimisation
- optimisation
- parse selection
- parser
- parsing
- part-of-speech tagging
- pos tagger
- pos tagging
- pre-processing
- preprocessing
- processing
- quasi-newton optimisation
- resource translation
- search
- segmentation
- sequence labeling
- sequential tagging
- supertagging
- tagger
- tagger implementation
- tagging
- tokenisation
- transformation-based learning
- viterbi
- viterbi algorithm
Other assigned terms:
- affixes
- annotation
- approach
- association for computational linguistics
- baseline model
- beam
- benchmark
- bigram
- case
- composition
- conditional distribution
- context features
- crf model
- data set
- data sets
- data sparseness
- density function
- distribution
- english grammar
- english verb
- english verb particle
- estimation
- f-score
- fact
- feature
- feature description
- feature set
- feature space
- gaussian prior
- grammar
- grammar developer
- grammars
- hpsgs
- implementation
- joint probability
- kanji
- katakana
- knowledge
- labeling
- language resource
- leaf
- lexeme
- lexemes
- lexical entry
- lexical feature
- lexical features
- lexical information
- lexical item
- lexical items
- lexical rules
- lexical type
- lexicon
- likelihood
- linguistic
- linguistics
- log-linear models
- mapping
- mark-up
- measure
- method
- methodology
- model parameters
- multiword expressions
- mwes
- natural language
- nouns
- orthography
- parse
- part-of-speech
- particle
- penn treebank
- phrase
- phrase structure
- phrase structure grammars
- posterior
- posterior probability
- precision
- prefixes and suffixes
- prior distribution
- probability
- probability density
- probability density function
- process
- punctuation
- relation
- search space
- semantic
- semantic relation
- semantic representation
- sentence
- sentences
- statistics
- stem
- suffixes
- supertags
- tag set
- tagalog
- tags
- tagset
- terms
- test data
- training
- training and test data
- training data
- training set
- transformation
- transformation rules
- treebank
- treebank annotation
- trigram
- type hierarchy
- unigram
- verb
- word
- word classes
- words
