ACL RD-TEC 1.0 Summarization of N04-4010
Paper Title:
USING N-BEST LISTS FOR NAMED ENTITY RECOGNITION FROM CHINESE SPEECH
USING N-BEST LISTS FOR NAMED ENTITY RECOGNITION FROM CHINESE SPEECH
Authors: Lufeng Zhai and Pascale Fung and Richard Schwartz and Marine Carpuat and Dekai Wu
Primarily assigned technology terms:
- algorithm
- asr system
- automatic content extraction
- bracketing
- capitalization
- chinese speech ner
- classification
- computational linguistics
- corpus annotation
- discriminative training
- english ner
- entity recognition
- hidden markov
- hidden markov model
- identification\/classification
- information extraction
- information retrieval
- information retrieval and extraction
- iterative scaling
- language learning
- language processing
- learning
- lvcsr
- markov model
- maxent
- maximum entropy
- maximum entropy model
- maximum-entropy
- message understanding
- modeling
- n-best voting
- named entity recognition
- natural language learning
- natural language processing
- ne classification
- ner evaluation
- normalization
- one-pass identification\/classification
- processing
- recognition
- segmentation
- segmenter
- speech recognition
- stochastic process
- text to speech
- transcription
- voting
- weighted voting
- word segmentation
Other assigned terms:
- annotated corpora
- annotation
- approach
- asr output
- broadcast news
- broadcast news data
- byblos system
- character error rate
- chinese text
- chinese text corpus
- chinese words
- confidence measure
- corpora
- distribution
- duration
- english speech
- entropy
- error rate
- evaluation set
- f-measure
- feature
- hmm model
- hypotheses
- hypothesis
- implementation
- language model
- lattices
- linguistics
- maxent model
- maximum entropy principle
- measure
- message
- message understanding conference
- method
- named entities
- named entity
- named-entity
- names
- natural language
- ner model
- nist
- normalization factor
- part-of-speech
- part-of-speech tag
- part-of-speech tags
- person names
- pfr corpus
- precision
- probability
- probability distribution
- process
- punctuation
- recognition accuracy
- recognition errors
- recognition evaluation
- sentence
- sentences
- silence
- speech recognition accuracy
- spoken language
- syntactic patterns
- tags
- test data
- text
- text corpus
- training
- training data
- understanding
- uniform probability
- utterance
- vocabulary
- word
- word boundaries
- word lattices
- word-based model
- words
