Similarity-Based Alignment of Monolingual Corpora for Text Simplification Purposes.
Sarah AlbertssonEvelina RennesArne JönssonPublished in: CL4LC@COLING 2016 (2016)
Keyphrases
- machine translation system
- parallel texts
- word alignment
- sentence pairs
- information retrieval
- text data
- parallel corpus
- text corpora
- text retrieval
- query expansion
- statistical machine translation
- topic segmentation
- multiresolution
- chinese english
- question answering
- text mining
- machine translation
- cross language
- cross language information retrieval
- cross lingual
- text collections
- document corpus
- text corpus
- lexico syntactic
- text classification
- parallel corpora
- document retrieval
- word level
- source language
- linguistic resources
- comparable corpora
- word frequency
- text documents
- document collections
- linguistic patterns
- domain specific
- keywords
- machine learning