Massively Multilingual Document Alignment with Cross-lingual Sentence-Mover's Distance.
Ahmed El-KishkyFrancisco GuzmánPublished in: AACL/IJCNLP (2020)
Keyphrases
- cross lingual
- word level
- language independent
- machine translation
- word alignment
- source language
- parallel corpus
- document clustering
- cross language
- cross lingual information retrieval
- language modeling
- multi lingual
- sentiment classification
- text classification
- word sense
- document images
- natural language
- parallel corpora
- cross language information retrieval
- language model
- document collections
- query translation
- sentence level
- statistical machine translation
- monolingual and cross lingual
- web news
- language specific
- news articles
- distance measure
- text summarization
- translation model
- text documents
- information retrieval
- natural language processing
- query expansion
- target language
- machine translation system
- information retrieval systems
- information extraction
- chinese english
- document retrieval
- cross document
- indian languages
- retrieval systems
- bilingual dictionaries
- tf idf
- web documents
- relevance model