ACL RD-TEC 1.0 Summarization of W05-0709
Paper Title:
THE IMPACT OF MORPHOLOGICAL STEMMING ON ARABIC MENTION DETECTION AND COREFERENCE RESOLUTION
THE IMPACT OF MORPHOLOGICAL STEMMING ON ARABIC MENTION DETECTION AND COREFERENCE RESOLUTION
Authors: Imed Zitouni and Jeffrey Sorensen and Xiaoqiang Luo and Radu Florian
Primarily assigned technology terms:
- algorithm
- approximation
- automatic content extraction
- bootstrapping
- chinese segmentation
- classification
- classifier
- classifiers
- computational linguistics
- coreference resolution
- coreference resolution system
- coreference system
- data mining
- detection and tracking
- entity detection
- entity detection and tracking
- entity recognition
- entity recognition system
- extraction program
- finite state
- finite state machine
- finite state machines
- grouping
- inflectional process
- information extraction
- information extraction tasks
- information retrieval
- language processing
- language understanding
- linking
- machine translation
- markov model
- matching
- maxent
- maximum entropy
- maximum entropy model
- maximum-entropy
- mention detection
- mention detection task
- mining
- model building
- morphological processing
- morphology
- named entity recognition
- natural language processing
- parsing
- partial string match
- preprocessing
- processing
- question answering
- recognition
- recognition system
- regular expression
- segmentation
- segmentation process
- segmentation system
- segmenter
- sequence classification
- shallow parsing
- string match
- summarization
- supervised training
- tagging
- tree algorithm
- type detection
- unsupervised training
- word-for-word translation
Other assigned terms:
- accusative case
- affixes
- agglutinative language
- alphabet
- approach
- arabic language
- arabic morphology
- arabic text
- arabic treebank
- association for computational linguistics
- backoff
- backoff language model
- case
- characters
- chunks
- classification problem
- community
- composition
- contextual information
- coreference resolution performance
- corpora
- data sparseness
- data sparseness problem
- detection task
- development set
- dictionary
- dictionary entries
- discourse
- entity type
- entropy
- entropy markov model
- evaluation metric
- exact match
- experimental results
- f-measure
- fact
- feature
- feature set
- feature types
- gazetteer
- gazetteer information
- genitive case
- implementation
- language model
- language processing applications
- lattice
- lexical features
- lexical set
- linguistics
- linguistics literature
- maximum entropy principle
- maximum-entropy model
- meaning
- measure
- morphemes
- morphological structure
- n-gram
- n-gram model
- n-grams
- named entity
- named-entity
- natural language
- natural language processing applications
- nist
- nominals
- nouns
- parse
- parse tree
- parsing information
- precision
- prefixes and suffixes
- preposition
- prepositions
- probability
- probability distributions
- process
- pronoun
- pronouns
- punctuation
- recognition task
- segmentation accuracy
- segmented corpus
- segments
- semantic
- semantic tag
- semitic languages
- sentence
- sentence meaning
- sparseness problem
- statistical framework
- stem
- stems
- style
- suffix
- suffixes
- symbol
- synonyms
- syntactic features
- system description
- tags
- technique
- terms
- test data
- test set
- text
- tokens
- training
- training data
- training set
- translations
- tree
- treebank
- trigram
- trigram language model
- understanding
- unigram
- unigram model
- verb
- vocabulary
- word
- word form
- words
