ACL RD-TEC 1.0 Summarization of A97-1031
Paper Title:
AN INFORMATION EXTRACTION CORE SYSTEM FOR REAL WORLD GERMAN TEXT PROCESSING
AN INFORMATION EXTRACTION CORE SYSTEM FOR REAL WORLD GERMAN TEXT PROCESSING
Authors: Gunter Neumann and Rolf Backofen and Judith Baur and Markus Becker and Christian Braun
Primarily assigned technology terms:
- automatic extraction
- bottom-up grammar development
- browser
- compiler
- database
- deep analysis
- disambiguation
- domain-specific extraction
- domain-specific inference
- extraction system
- finite state
- finite state transducers
- fragment combination
- fragment extraction
- fragment processing
- german text processing
- grammar development
- grammar writer
- group recognition
- inference system
- information extraction
- information extraction system
- information systems
- instantiation
- language technology
- learning
- learning methods
- lexical retrieval
- matching
- message understanding
- morphological processing
- morphology
- nlp
- parser
- parsing
- part-of-speech disambiguation
- processing
- reading
- recognition
- recursive trie traversal
- reference resolution
- regular expression
- searching
- shallow analysis
- shallow parser
- shallow parsing
- shallow processing
- spelling
- splitting
- structure recognition
- subcategorization
- tagger
- tagging
- task-specific reference resolution
- template construction\/instantiation
- template generation
- text processing
- text scanning
- tile
- tokenizer
- transducers
- verb subcategorization
Other assigned terms:
- abbreviations
- adjective
- anchor
- anchors
- appointment scheduling
- approach
- auxiliary verbs
- case
- characters
- compounding
- compounds
- contextual information
- control flow
- corpora
- customization
- dependency theory
- description language
- determiner
- device
- domain knowledge
- english text
- exact match
- extraction patterns
- fact
- feature
- feature value
- finite state grammar
- formalism
- formalisms
- frame
- free word order
- generation
- german language
- german text
- grammar
- grammars
- hand-tagged corpora
- head-modifier structure
- implementation
- inference rules
- inflection
- inflectional information
- input string
- input text
- knowledge
- knowledge base
- lexical entries
- lexical entry
- lexical information
- lexical rules
- lexicon
- linguistic
- linguistic information
- linguistic knowledge
- lisp
- main verb
- measure
- mechanisms
- message
- message understanding conference
- method
- morpho-syntactic information
- morphological component
- names
- natural language
- nominal phrase
- nouns
- np fragment
- paragraph
- paragraphs
- part of speech
- part-of-speech
- particle
- partof-speech
- person names
- phrase
- portability
- precision
- prepositional phrases
- process
- pronouns
- proper name
- proper names
- punctuation
- quantifier
- recognition rate
- regular expressions
- semantic
- semantic constraints
- sentence
- sentences
- server
- slot
- speech act
- stem
- stems
- subcategorization frames
- subgrammar
- subsumption
- suffix
- symbol
- syntactic agreement
- tagged corpora
- tagging accuracy
- technologies
- technology
- template structure
- text
- text corpus
- text structure
- theory
- time expressions
- tokens
- topics
- training
- training set
- transitive verb
- transitive verbs
- typed feature
- unannotated corpora
- understanding
- untagged corpora
- user
- verb
- verb forms
- verb frame
- verb group
- verb groups
- word
- word form
- word level
- word order
- words
