HuaAMS at SemEval-2022 Task 8: Combining Translation and Domain Pre-training for Cross-lingual News Article Similarity.
Sai Sandeep Sharma ChittillaTalaat KhalilPublished in: SemEval@NAACL (2022)
Keyphrases
- cross lingual
- news articles
- machine translation
- event extraction
- cross lingual information retrieval
- cross language
- translation model
- query translation
- parallel corpora
- parallel corpus
- statistical machine translation
- machine translation system
- language independent
- similarity measure
- transfer learning
- word sense disambiguation
- language modeling
- online news
- bilingual dictionaries
- web news
- cross language information retrieval
- news stories
- text documents
- training set
- natural language processing
- source language
- semantic similarity
- document clustering
- supervised learning
- information extraction
- knowledge base
- target language
- active learning
- reinforcement learning
- search engine