Computational analyses of the topics, sentiments, literariness, creativity and beauty of texts in a large Corpus of English Literature.
Arthur M. JacobsAnnette KinderPublished in: CoRR (2022)
Keyphrases
- newspaper articles
- english words
- training corpus
- word sense
- news articles
- natural language
- brazilian portuguese
- statistical machine translation
- link grammar
- linguistic features
- open domain
- person names
- keywords
- manually generated
- natural language text
- linguistic analysis
- wide coverage
- scientific papers
- short texts
- sentiment analysis
- news stories
- broad coverage
- machine translation
- cross lingual
- unknown words
- stop words
- social media
- topic models
- linguistic information
- language learning
- multiword
- native language
- text classification
- world knowledge
- writing style
- text corpus
- information extraction
- text corpora
- wordnet
- text documents
- topic detection and tracking
- information extraction systems
- word pairs
- answer questions
- sentence level
- sentence pairs