ACL RD-TEC 1.0 Summarization of W06-2914
Paper Title:
WORD DISTRIBUTIONS FOR THEMATIC SEGMENTATION IN A SUPPORT VECTOR MACHINE APPROACH
WORD DISTRIBUTIONS FOR THEMATIC SEGMENTATION IN A SUPPORT VECTOR MACHINE APPROACH
Authors: Maria Georgescul and Alexander Clark and Susan Armstrong
Primarily assigned technology terms:
- algorithm
- anaphora resolution
- automatic summarisation
- binary classification
- classification
- classifier
- clustering
- clustering algorithm
- computational linguistics
- computational natural language learning
- computer science
- computing
- cross validation
- cross-validation
- data representation
- decision tree
- decision tree classifier
- decomposition
- detection and tracking
- dimensionality reduction
- discourse understanding
- distance function
- document browsing
- dynamic programming
- dynamic programming algorithm
- evaluation procedure
- feature selection
- five-fold cross validation
- hidden markov
- hidden markov model
- identification
- information management
- information retrieval
- inner product
- kernel
- kernels
- language learning
- latent semantic analysis
- learner
- learning
- learning approach
- learning task
- lemmatization
- likelihood estimation
- linear learning
- machine learning
- mapping function
- markov model
- maximum likelihood
- maximum likelihood estimation
- measuring
- model selection
- modeling
- natural language learning
- optimisation
- programming algorithm
- radial basis function
- regression
- regularization
- risk minimization
- sampling
- search
- segment identification
- segmentation
- segmentation method
- segmenter
- semantic analysis
- singular value decomposition
- story segmentation
- summarisation
- supervised learning
- supervised learning approach
- support vector classifier
- support vector machine
- support vector machines
- svm approach
- svm learning
- svm-based system
- term weighting
- thematic segmentation
- tokenization
- topic detection
- topic detection and tracking
- topic segmentation
- transcription
- tree classifier
- validation
- vector learning
- vector machine learning
- vector space representation
- weighting
Other assigned terms:
- anaphora
- annotators
- approach
- association for computational linguistics
- bag of words
- bias
- binary classification problem
- broadcast news
- brown corpus
- classification problem
- coherence
- cohesion
- computational complexity
- conditional independence
- conll-x
- corpora
- correlation
- cosine distance
- data set
- data sets
- dialogues
- dimensionality
- discourse
- discourse topic
- distribution
- document
- document collections
- document structure
- empirical evaluation
- entropy
- error metric
- error rate
- estimation
- evaluation measures
- evaluation metrics
- experimental results
- fact
- feature
- feature space
- frequency counts
- genre
- gold standard
- grid
- human annotators
- hypothesis
- hypothesis space
- intention
- inter-annotator agreement
- kernel function
- knowledge
- labeling
- latent semantic
- learning machine
- lemma
- lexical level
- likelihood
- linear algebra
- linguistics
- log-likelihood
- mapping
- measure
- measures
- method
- methodology
- multimodal information
- natural language
- optimisation problem
- paragraphs
- parameter settings
- parameter values
- parametric model
- precision
- procedure
- pronouns
- prosodic information
- regularization parameter
- relation
- representations
- risk minimization principle
- segment boundaries
- segments
- semantic
- sentence
- sentences
- similarity measure
- statistical significance
- support vector
- svms
- system performance
- technique
- term
- term weighting scheme
- test set
- text
- text collection
- text segment
- textual structure
- thematic segment
- theory
- topic shift
- topics
- training
- training data
- training example
- training examples
- training set
- training time
- transcriptions
- transformation
- tree
- understanding
- utterance
- vector space
- vocabulary
- weighting scheme
- word
- word distribution
- word frequencies
- word frequency
- word level
- words
