ACL RD-TEC 1.0 Summarization of C02-2025
Paper Title:
THE LINGO REDWOODS TREEBANK: MOTIVATION AND PRELIMINARY APPLICATIONS
THE LINGO REDWOODS TREEBANK: MOTIVATION AND PRELIMINARY APPLICATIONS
Authors: Stephan Oepen and Kristina Toutanova and Stuart Shieber and Christopher Manning and Dan Flickinger and Thorsten Brants
Primarily assigned technology terms:
- analysis engines
- cross-validation
- database
- development environment
- disambiguation
- grammar development
- grammar development environment
- groningen
- hmm tagger
- learning
- learning approaches
- lexical selection
- likelihood estimate
- linear interpolation
- machine learning
- machine learning approaches
- maximum likelihood
- meaning representation
- nlp
- optimization
- parse disambiguation
- parse ranking
- parse selection
- parser
- parsing
- part-of-speech tagging
- probabilistic parsing
- probabilistic processing
- processing
- ranking
- regression
- regression test
- scoring
- statistical techniques
- stochastic parsing
- tagger
- tagging
- ten-fold cross-validation
- tree comparison
- tree selection
- treebank construction
- treebanking
- unification
- unigram tagger
Other assigned terms:
- adjunct
- ambiguity
- analogy
- anchor
- annotation
- annotators
- appointment scheduling
- approach
- broad-coverage grammar
- case
- context free grammar
- context information
- context-free grammar
- corpora
- corpus size
- data set
- dependency structures
- dependency treebank
- derivation
- derivation tree
- derivation trees
- derivations
- dialogues
- disambiguation system
- disambiguation task
- distribution
- dutch
- experimental results
- expert knowledge
- forest
- generation
- genre
- gold standard
- grammar
- grammar rules
- grammars
- grammatical coverage
- grammatical representation
- head-driven phrase structure grammar
- hpsg
- hpsg grammar
- hpsg-like grammar
- interpolation
- interpretation
- joint probability
- joint probability distribution
- knowledge
- language corpora
- lexical items
- lexical type
- likelihood
- linguistic
- linguistic data
- linguistic expression
- linguistic framework
- linguistic information
- linguistic system
- linguistics
- local tree
- log-linear model
- log-linear models
- mappings
- maximum likelihood estimate
- meaning
- method
- methodology
- nonterminals
- oracle
- parse
- parse forest
- parse tree
- parsed corpus
- parsing problem
- parsing research
- part-of-speech
- part-of-speech tags
- pcfg
- pcfg model
- penn treebank
- phrase
- phrase structure
- phrase structure grammar
- phrase structure tree
- phrase structure trees
- prague dependency treebank
- probabilistic model
- probabilities
- probability
- probability distribution
- probability distributions
- procedure
- process
- production rule
- redwoods treebank
- relation
- seed
- semantic
- semantic interpretation
- sentence
- sentences
- sequence model
- statistical models
- stochastic model
- syntax
- tag model
- tag sequence
- tagging accuracy
- tagging model
- tagging task
- tags
- technology
- test corpus
- test set
- text
- text genre
- theories
- tiger corpus
- training
- training data
- training set
- transformation
- tree
- treebank
- trees
- trigram
- understanding
- unification-based grammar
- uniform distribution
- unigram
- utterance
- verbmobil corpus
- word
- word sequence
- words
