ACL RD-TEC 1.0 Summarization of W03-1110
Paper Title:
ISSUES IN PRE- AND POST-TRANSLATION DOCUMENT EXPANSION: UNTRANSLATABLE COGNATES AND MISSEGMENTED WORDS
ISSUES IN PRE- AND POST-TRANSLATION DOCUMENT EXPANSION: UNTRANSLATABLE COGNATES AND MISSEGMENTED WORDS
Primarily assigned technology terms:
- automatic recognition
- automatic speech recognition
- automatic speech recognizer
- cognate matching
- cross-language information retrieval
- cross-language retrieval
- detection and tracking
- document expansion
- document processing
- document retrieval
- document translation
- grouping
- indexing
- information retrieval
- information retrieval task
- inquery retrieval system
- matching
- monolingual speech retrieval
- post-translation document expansion
- post-translation expansion
- pre-translation document expansion
- processing
- query expansion
- query formulation
- query language
- query translation
- ranking
- recognition
- recognition system
- recognizer
- retrieval system
- search
- segmentation
- segmentation process
- segmenter
- speech recognition
- speech recognition system
- speech recognizer
- speech retrieval
- spoken document retrieval
- terminology
- topic detection
- topic detection and tracking
- transcription
- transliteration
- weighting
- word-for-word translation
Other assigned terms:
- alphabet
- approach
- bigram
- bilingual term
- broadcast news
- case
- coherence
- concept
- concepts
- dictionary
- distribution
- document
- document collection
- document frequency
- english query
- english text
- english translations
- experimental results
- fact
- information need
- inverse document frequency
- knowledge
- language pairs
- language unigram frequency
- lexicon
- mandarin chinese
- mean average precision
- monolingual query
- monolingual speech
- named entities
- names
- noise
- organization names
- orthography
- performance evaluation
- precision
- probability
- process
- proper names
- queries
- query
- retrieval task
- russian
- signal
- statistic
- statistics
- target language
- technique
- term
- term list
- terms
- text
- text collection
- text corpus
- topics
- training
- transcript
- transcriptions
- transcripts
- translation lexicon
- translations
- understanding
- unigram
- word
- word boundaries
- word lists
- words
