ACL RD-TEC 1.0 Summarization of W06-1626
Paper Title:
DISTRIBUTED LANGUAGE MODELING FOR $N$-BEST LIST RE-RANKING
DISTRIBUTED LANGUAGE MODELING FOR $N$-BEST LIST RE-RANKING
Authors: Ying Zhang and Almut Silja Hildebrand and Stephan Vogel
Primarily assigned technology terms:
- algorithm
- approximation
- automatic speech recognition
- bootstrapping
- bootstrapping method
- computational linguistics
- computing
- decoder
- decoding
- finite state
- information retrieval
- kneser-ney smoothing
- language model adaptation
- language modeling
- language modeling approach
- language processing
- likelihood estimate
- list re-ranking
- list reranking
- machine translation
- matching
- maximum likelihood
- model adaptation
- modeling
- n-best list re-ranking
- n-best list reranking
- n-best re-ranking
- n-gram language modeling
- n-gram matching
- natural language processing
- nlp
- parallel processing
- phrase-based translation
- probability estimation
- processing
- processor
- re-ranking
- recognition
- relevance weighting
- relevance weighting and selection
- reranking
- search
- search algorithm
- smoothing
- smt system
- speech recognition
- statistical language modeling
- statistical machine translation
- weighting
Other assigned terms:
- ambiguity
- approach
- array
- association for computational linguistics
- asymmetric relationship
- bleu
- bleu metric
- bleu score
- bleu scores
- chunk
- chunks
- client\/server architecture
- community
- concept
- conditional probabilities
- conditional probability
- corpora
- corpus size
- cosine distance
- disk
- distribution
- document
- document collection
- english corpus
- english sentence
- english translations
- estimation
- evaluation set
- exact match
- hypotheses
- hypothesis
- index
- language model
- language models
- language processing applications
- large corpus
- large training
- large training corpora
- lattice
- likelihood
- linguistics
- maximum likelihood estimate
- measure
- measures
- method
- monolingual corpus
- mutual information
- n-best list
- n-gram
- n-gram language model
- n-gram model
- n-grams
- natural language
- natural language processing applications
- nlp community
- non-compositionality
- oracle
- phrase-based system
- phrase-based translation model
- possible translation
- probabilities
- probability
- process
- query
- relevance measurement
- sentence
- sentence level
- sentences
- server
- source language
- source language sentence
- source sentence
- spurious ambiguity
- statistics
- suffix
- term
- test data
- test set
- training
- training corpora
- training data
- translation accuracy
- translation hypothesis
- translation model
- translation output
- translation quality
- translations
- trigram
- trigram language model
- unigram
- vocabulary
- vocabulary size
- word
- word data
- word sequence
- word sequences
- word types
- words
