ACL RD-TEC 1.0 Summarization of W04-3219
Paper Title:
MONOLINGUAL MACHINE TRANSLATION FOR PARAPHRASE GENERATION
MONOLINGUAL MACHINE TRANSLATION FOR PARAPHRASE GENERATION
Authors: Chris Quirk and Chris Brockett and William Dolan
Primarily assigned technology terms:
- algorithm
- alignment algorithm
- automatic alignment
- best-of-breed paraphrasing
- bidirectional alignment
- bigram clustering
- blind evaluation
- bootstrap
- classifiers
- clustering
- computing
- data collection
- database
- decoder
- decoding
- decomposition
- dynamic programming
- dynamic programming approach
- example-based machine translation
- giza
- identification
- identity mapping
- internet
- interpolated kneser-ney smoothing
- kneser-ney smoothing
- learning
- learning techniques
- levenshtein
- lexical selection
- machine learning
- machine learning techniques
- machine translation
- matching
- mt systems
- multisequence alignment
- paraphrase generation
- paraphrase identification
- paraphrase learning
- paraphrase learning and generation
- paraphrasing
- parsing
- phrasal translation
- post-processing
- preprocessing
- ranking
- ranking algorithm
- reporting
- scoring
- search
- smoothing
- statistical clustering
- statistical machine translation
- string matching
- syntactic reordering
- translation systems
- viterbi
- viterbi algorithm
- word alignment
- world wide web
Other assigned terms:
- aligned sentence
- alignment error rate
- annotation
- annotators
- approach
- authorship
- bias
- bigram
- bilingual lexicon
- case
- chunks
- cluster
- clusters
- coherence
- corpora
- correlation
- data set
- data sets
- data sparsity
- derivation
- document
- document structure
- edit distance
- error rate
- evaluation methodology
- evaluation metric
- events
- f-measure
- generation
- gold standard
- human judgments
- hypothesis
- ibm model
- ibm models
- implementation
- inference rules
- information content
- inter-rater agreement
- language model
- lattice
- lattices
- levenshtein distance
- lexical translation
- lexicon
- linguistic
- linguistic features
- mapping
- mappings
- meaning
- method
- methodology
- monolingual corpora
- monolingual paraphrase
- named entity
- news corpus
- parallel corpora
- paraphrase
- paraphrases
- phrase
- precision
- probabilities
- probability
- process
- programming approach
- punctuation
- random order
- regular expressions
- reordering
- running time
- scalability
- semantic
- semantic domain
- sentence
- sentence pair
- sentences
- source sentence
- source text
- synonym
- synonymy
- synset
- target language
- target language model
- target languages
- target sentence
- technique
- terms
- text
- text structure
- tokens
- training
- training corpus
- training data
- translation probabilities
- translation quality
- translations
- trigram
- trigram language model
- trigram model
- uniform probability
- vocabulary
- word
- word lattice
- word sequences
- wordnet
- wordnet synset
- words
