ACL RD-TEC 1.0 Summarization of E06-1040
Paper Title:
COMPARING AUTOMATIC AND HUMAN EVALUATION OF NLG SYSTEMS
COMPARING AUTOMATIC AND HUMAN EVALUATION OF NLG SYSTEMS
Authors: Anja Belz and Ehud Reiter
Primarily assigned technology terms:
- automatic evaluation
- candidate generation
- chunker
- content determination
- content representation
- corpus analysis
- corpus-based evaluation
- cross-validation
- data analysis
- document summarisation
- generation framework
- indexing
- language generation
- measuring
- microplanning
- mt systems
- natural language generation
- nlg system
- nlp
- parser
- pearson correlation
- predictor
- random generation
- ranking
- rating
- reading
- segmentation
- statistical generation
- statistical nlg systems
- summarisation
- validation
Other assigned terms:
- bleu
- bleu metric
- bleu score
- bleu scores
- case
- community
- corpora
- corpus frequency
- correlation
- cross-system evaluation
- data set
- distribution
- document
- evaluation measures
- evaluation metric
- evaluation metrics
- evaluations
- fact
- generation
- gold standard
- grammar
- human judgments
- hypothesis
- index
- language model
- likelihood
- measures
- method
- mt evaluation
- n-gram
- n-gram language model
- n-gram models
- n-grams
- natural language
- nist
- nlg community
- null hypothesis
- opinion
- opinions
- phrase
- precision
- probabilities
- probability
- probability distribution
- procedure
- process
- raw text corpora
- reference translations
- sentences
- statistic
- sublanguage
- syntactic structures
- task performance
- technique
- term
- terms
- testing data
- text
- text corpora
- text quality
- toolkit
- training
- training and testing data
- training data
- translation quality
- translations
- word
- words
