Text Detoxification as Style Transfer in English and Hindi.
Sourabrata MukherjeeAkanksha BansalAtul Kr. OjhaJohn P. McCraeOndrej DusekPublished in: CoRR (2024)
Keyphrases
- language identification
- proper names
- indian languages
- english text
- machine translation
- english language
- broad coverage
- named entity recognition
- named entity recognizer
- text to speech
- statistical machine translation
- linguistic analysis
- cross lingual
- natural language generation
- english words
- text mining
- natural language processing
- noun phrases
- target language
- named entities
- language specific
- open domain
- document images
- text documents
- manually constructed
- keywords
- multiword
- natural language
- authorship attribution
- comparable corpora
- contextual features
- word level
- source language
- text retrieval
- text classification
- cross language
- spoken language
- machine translation system
- document analysis
- query translation
- cross domain