ParaLaw Nets - Cross-lingual Sentence-level Pretraining for Legal Text Processing.
Ha-Thanh NguyenVu TranPhuong Minh NguyenThi-Hai-Yen VuongQuan Minh BuiChau Minh NguyenTran Binh DangMinh Le NguyenKen SatohPublished in: CoRR (2021)
Keyphrases
- text processing
- cross lingual
- sentence level
- sentiment classification
- sentiment analysis
- machine translation
- natural language processing
- text mining
- text classification
- parallel corpora
- information extraction
- language modeling
- language independent
- document clustering
- machine learning
- novelty detection
- transfer learning
- n gram
- information retrieval
- news articles
- word sense disambiguation
- keywords
- feature selection
- natural language
- text documents
- multi document summarization
- relevance model
- co occurrence
- databases