ACL RD-TEC 1.0 Summarization of E06-1035
Paper Title:
AUTOMATIC SEGMENTATION OF MULTIPARTY DIALOGUE
AUTOMATIC SEGMENTATION OF MULTIPARTY DIALOGUE
Authors: Pei-yun Hsueh and Johanna D. Moore and Steve Renals
Primarily assigned technology terms:
- algorithm
- asr system
- asr transcription
- automatic segmentation
- automatic speech recognition
- automatic topic segmentation
- binary classification
- boundary prediction
- chi-square test
- classification
- classifier
- classifiers
- computing
- cross validation
- crossvalidation
- data collection
- decision trees
- disfluency detection
- document browsing
- hidden markov
- hidden markov model
- hidden markov models
- language model training
- learning
- learning approaches
- length normalization
- linear regression
- linking
- machine learning
- machine learning approaches
- markov model
- maximum likelihood
- model training
- monte carlo algorithm
- monte carlo simulation
- news story segmentation
- normalization
- question-answering
- recognition
- regression
- sampling
- search
- segmentation
- sentence segmentation
- speech recognition
- spoken multiparty dialogue
- story segmentation
- supervised learning
- text segmentation
- texttiling
- topic segmentation
- transcription
- validation
- web search
Other assigned terms:
- acoustic models
- anchor
- annotation
- annotators
- approach
- asr output
- baseline model
- binary classification task
- broadcast news
- chi-square statistic
- class distribution
- classification task
- cohesion
- conversation
- conversational telephone speech
- cosine similarity
- cue phrase
- cue phrases
- cue words
- data set
- dialogues
- discourse
- distribution
- document
- error rate
- evaluation metrics
- fact
- feature
- gaussian mixture
- gaussian mixture model
- human annotators
- hypothesis
- icsi meeting corpus
- kappa
- language model
- language models
- lexical chains
- lexical cohesion
- lexical cohesion information
- lexical-cohesion
- likelihood
- markov models
- measures
- meeting corpus
- method
- opinion
- paragraph
- part-of-speech
- part-of-speech tags
- pause
- perplexity
- phrase
- prediction task
- probabilistic models
- probabilities
- probability
- procedure
- process
- segment boundaries
- segment boundary
- segments
- sentence
- set size
- silence
- speaker activity
- statistic
- statistics
- tags
- technique
- term
- terms
- test set
- text
- topic shift
- topics
- training
- training data
- training phase
- training set
- training set size
- transcript
- transcriptions
- transcripts
- trees
- trigram
- trigram language model
- unigram
- user
- utterance
- vocabulary
- vocal tract
- window size
- word
- word error rate
- word features
- word pair
- words