ACL RD-TEC 1.0 Summarization of N04-1015
Paper Title:
CATCHING THE DRIFT: PROBABILISTIC CONTENT MODELS, WITH APPLICATIONS TO GENERATION AND SUMMARIZATION
CATCHING THE DRIFT: PROBABILISTIC CONTENT MODELS, WITH APPLICATIONS TO GENERATION AND SUMMARIZATION
Authors: Regina Barzilay and Lillian Lee
Primarily assigned technology terms:
- algorithm
- approximation
- approximation algorithm
- binary classification
- classification
- classifier
- clustering
- complete-link clustering
- computing
- concept-to-text generation
- content-model-based learning
- content-model-based summarization
- content-selection
- database
- decoding
- document clustering
- document understanding
- extractive summarization
- hidden markov
- hidden markov models
- hmm induction
- hmms
- induction
- induction algorithm
- information ordering
- information selection
- language modeling
- language processing
- learning
- learning algorithm
- learning algorithms
- measuring
- model construction
- modeling
- multi-document summarization
- natural language processing
- parallel training
- parameter estimation
- parameter tuning
- parameterization
- partitioning
- planner
- processing
- ranking
- re-estimation
- re-estimation procedure
- recognition
- search
- segmentation
- sentence selection
- single-document summarization
- smoothing
- summarization
- summarization system
- summarization systems
- text generation
- text segmentation
- text summarization
- training algorithm
- tuning
- viterbi
- viterbi algorithm
- viterbi decoding
- viterbi-style approximation
Other assigned terms:
- american news corpus
- approach
- bigram
- bigram language model
- binary classification problem
- classification problem
- cluster
- clusters
- cognitive
- comprehension
- computational models
- concreteness
- corpora
- correlation
- data sparseness
- development set
- discourse
- distribution
- distributional information
- document
- document collections
- document content
- document structure
- domain knowledge
- domain-specific knowledge
- empirical results
- estimation
- evaluation metric
- evaluations
- fact
- feature
- feature set
- formalism
- formalisms
- generation
- grid
- hypothesis
- implementation
- input text
- knowledge
- knowledge base
- language model
- language models
- language-modeling research
- lexical similarity
- linguistic
- linguistic information
- markov models
- measure
- measures
- method
- model parameters
- model size
- names
- natural language
- news corpus
- paragraph
- paragraphs
- parallel corpus
- parameter values
- permutation
- priori
- probabilities
- probability
- probability estimates
- procedure
- process
- proper names
- relation
- representations
- rhetorical relations
- runtime
- schema
- sentence
- sentence similarity
- sentences
- state-specific language model
- stems
- summarization task
- system performance
- technique
- term
- terms
- text
- text structure
- tokens
- topics
- training
- training corpora
- training data
- training set
- transition probabilities
- understanding
- vocabulary
- vocabulary size
- word
- word distribution
- word sequence
- words
