SkoltechNLP at SemEval-2021 Task 2: Generating Cross-Lingual Training Data for the Word-in-Context Task.
Anton RazzhigaevNikolay ArefyevAlexander PanchenkoPublished in: SemEval@ACL/IJCNLP (2021)
Keyphrases
- cross lingual
- word sense
- training data
- word sense disambiguation
- translation model
- machine translation
- parallel corpus
- language modeling
- language independent
- target word
- machine translation system
- cross language
- word alignment
- cross lingual information retrieval
- word segmentation
- co occurrence
- n gram
- statistical machine translation
- training set
- text classification
- indian languages
- language model
- decision trees
- supervised learning
- prior knowledge
- active learning
- news articles
- wordnet
- natural language processing
- document clustering
- source language
- parallel corpora
- bilingual dictionaries
- retrieval model
- transfer learning
- probabilistic model