Variation in noun and pronoun frequencies in a sociohistorical corpus of English.
Tanja SäilyTerttu NevalainenHarri SiirtolaPublished in: Lit. Linguistic Comput. (2011)
Keyphrases
- noun phrases
- pronoun resolution
- link grammar
- broad coverage
- penn treebank
- query translation
- natural language
- person names
- statistical machine translation
- reference resolution
- wide coverage
- open domain
- parallel corpus
- tree bank
- anaphora resolution
- parse tree
- coreference resolution
- word pairs
- english words
- english language
- natural language processing
- word sense disambiguation
- word sense
- wordnet
- sentence pairs
- machine translation
- training corpus
- semantic relations
- part of speech
- multiword
- linguistic features
- semantic roles
- unknown words
- cross language information retrieval
- pos tagging
- comparable corpora
- mono lingual
- parallel corpora
- machine translation system
- target language
- question answering
- cross lingual
- named entities
- frequency distribution
- answer questions
- text categorization
- stop words
- cross language