ACL RD-TEC 1.0 Summarization of C00-1012
Paper Title:
THE EFFECTS OF ANALYSING COHESION ON DOCUMENT SUMMARISATION
THE EFFECTS OF ANALYSING COHESION ON DOCUMENT SUMMARISATION
Authors: Branirnir K. Boguraev and Mary S. Neff
Primarily assigned technology terms:
- algorithm
- anaphora resolution
- boosting
- categorization
- computing
- content analysis
- content characterization
- content management
- coreference resolution
- cross-document coreference resolution
- cutoff
- database
- deep text understanding
- disambiguation
- discourse segmentation
- document analysis
- document categorization
- document management
- document processing
- document retrieval
- document summarisation
- document summarization
- ellipsis resolution
- extraction systems
- feature extraction
- frequency analysis
- grouping
- identification
- identificatkm
- information retrieval
- intrinsic evaluation
- lexical chaining
- linguistic analysis
- linguistic processing
- morphological analysis
- morphological processing
- name identification
- normalization
- paraphrasing
- processing
- pronominal anaphora resolution
- ranking
- recognition
- relation determination
- reporting
- robust text analysis
- scoring
- search
- segmentation
- segmentation process
- selection strategy
- sentence extraction
- sentence ranking
- sentence selection
- smnmarization
- structure identification
- sub-story identification
- summarisation
- summarization
- summarization procedure
- summarization process
- summarizer
- summary generation
- sumnlarization ftmction
- task-based evaluation
- text analysis
- text understanding
- tile
- tile summarizer
- tokenisation
- tuning
- word analysis
Other assigned terms:
- abbreviations
- anaphora
- anaphors
- annotation
- approach
- background corpus
- break
- canonical form
- case
- co-reference
- coherence
- cohesion
- collocation
- concept
- concepts
- content words
- contextual information
- cosine measure
- cross-document coreference
- cue phrases
- definite noun
- definite noun phrase
- derivation
- discourse
- discourse element
- discourse entities
- discourse entity
- discourse structure
- distribution
- document
- document collection
- document content
- document frequency
- document set
- document structure
- domain knowledge
- domain vocabulary
- ellipsis
- evaluation strategy
- experimental results
- expository text
- fact
- feature
- generation
- heuristic
- heuristic rules
- heuristics
- hierarchical representation
- input text
- inverse document frequency
- knowledge
- lemma
- lexical chains
- lexical cohesion
- lexical database
- lexical relation
- lexical relations
- lexical similarity
- linguistic
- linguistic feature
- linguistic information
- linguists
- local context
- logical structure
- mapping
- markup
- measure
- measures
- mechanisms
- metadata
- method
- named entity
- names
- noise
- noun phrase
- noun phrase anaphora
- paragraph
- paragraphs
- phrase
- polysemy
- precision
- priori
- procedure
- process
- pronominal anaphora
- proper name
- relation
- relative frequency
- rhetorical relations
- search time
- segment boundaries
- segments
- semantic
- sentence
- sentences
- statistical information
- statistical measure
- statistics
- systeln
- tags
- technical terms
- technology
- term
- term distribution
- terms
- test corpus
- test set
- text
- text cohesion
- topic shift
- topics
- training
- tree
- understanding
- user
- vocabulary
- word
- wordnet
- words
