Uppsala NLP at SemEval-2021 Task 2: Multilingual Language Models for Fine-tuning and Feature Extraction in Word-in-Context Disambiguation.
Huiling YouXingran ZhuSara StymnePublished in: SemEval@ACL/IJCNLP (2021)
Keyphrases
- language model
- word sense disambiguation
- fine tuning
- n gram
- word sense
- language modeling
- cross lingual
- context sensitive
- natural language processing
- translation model
- feature extraction
- cross language information retrieval
- wordnet
- sense disambiguation
- machine translation
- document retrieval
- target word
- cross language
- probabilistic model
- language modelling
- information retrieval
- part of speech
- language independent
- speech recognition
- co occurrence
- query terms
- statistical language models
- retrieval model
- query expansion
- test collection
- natural language
- ambiguous words
- information extraction
- statistical language modeling
- statistical machine translation
- relevance model
- word error rate
- word clouds
- multiword
- out of vocabulary
- search engine
- semantic similarity
- question answering
- bilingual dictionaries
- context dependent
- smoothing methods
- vector space model
- feature selection
- spoken term detection
- word segmentation
- language processing
- machine translation system
- retrieval effectiveness
- text documents
- relevant documents
- text mining
- language models for information retrieval