ACL RD-TEC 1.0 Summarization of E06-3004
Paper Title:
BOOTSTRAPPING NAMED ENTITY RECOGNITION WITH AUTOMATICALLY GENERATED GAZETTEER LISTS
BOOTSTRAPPING NAMED ENTITY RECOGNITION WITH AUTOMATICALLY GENERATED GAZETTEER LISTS
Primarily assigned technology terms:
- active learning
- adaboost
- algorithm
- automatic generation
- automatic information extraction
- bootstrapping
- bootstrapping process
- classification
- classification process
- classifier
- classifiers
- co-training
- decision trees
- disambiguation
- entity classification
- entity detection
- entity disambiguation
- entity recognition
- entity recognition system
- entity recognition systems
- feature construction
- feature extraction
- gazetteer2 construction
- hidden markov
- hidden markov models
- information extraction
- information retrieval
- learning
- learning algorithms
- learning approach
- learning approaches
- learning method
- learning techniques
- machine learning
- machine learning algorithms
- machine learning approach
- machine learning approaches
- machine learning techniques
- maximum entropy
- message understanding
- n-gram extraction
- named entity classification
- named entity detection
- named entity recognition
- ne recognizer
- nlp
- pattern validation
- preprocessing
- processing
- recognition
- recognition system
- recognition systems
- recognizer
- regular expression
- search
- searching
- self-training
- semi-supervised learning
- sense disambiguation
- supervised learning
- supervised method
- tagging
- validation
- word sense disambiguation
- world wide web
Other assigned terms:
- approach
- case
- characters
- classification tasks
- context words
- contextual information
- corpora
- data set
- dependency relation
- entity recognition task
- entropy
- evaluation measures
- events
- feature
- feature vectors
- gazetteer
- gazetteer information
- generation
- graph theory
- heterogeneous information
- implementation
- linguistic
- markov models
- measures
- message
- message understanding conferences
- method
- morphologic
- n-gram
- name entity
- named entities
- named entity
- names
- nlp tasks
- noise
- organization names
- parameter settings
- person names
- precision
- preposition
- prepositions
- process
- recognition task
- relation
- seed
- selection restriction
- semantic
- semantic information
- semi-supervised approach
- spanish language
- statistics
- subgraph
- syntactic information
- tags
- test data
- test set
- text
- theory
- training
- training data
- training examples
- tree
- trees
- trigram
- understanding
- unlabeled examples
- word
- word sense
- words
