Corpus Creation and Emotion Prediction for Hindi-English Code-Mixed Social Media Text.
Deepanshu VijayAditya BohraVinay SinghSyed Sarfaraz AkhtarManish ShrivastavaPublished in: NAACL-HLT (Student Research Workshop) (2018)
Keyphrases
- english words
- social media
- broad coverage
- statistical machine translation
- proper names
- language identification
- open domain
- machine translation
- mono lingual
- training corpus
- comparable corpora
- cross lingual
- indian languages
- machine translation system
- noun phrases
- multiword
- english text
- chinese english
- text corpora
- english language
- contextual features
- natural language processing
- target language
- sentence level
- text corpus
- source language
- spoken language
- link grammar
- text to speech synthesis
- word sense
- recognizing textual entailment
- person names
- spontaneous speech
- information extraction
- word pairs
- text to speech
- natural language text
- cross language information retrieval
- named entity recognition
- document corpus
- lexical features
- co occurrence
- source code
- stop words
- named entities
- language specific
- text data
- unknown words
- parallel corpora
- named entity recognizer
- information retrieval
- document level
- natural language
- text retrieval
- reading comprehension
- linguistic features