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: CoRR (2021)
Keyphrases
- language model
- word sense disambiguation
- fine tuning
- word sense
- n gram
- language modeling
- context sensitive
- cross lingual
- natural language processing
- feature extraction
- translation model
- wordnet
- cross language information retrieval
- sense disambiguation
- target word
- document retrieval
- language independent
- information retrieval
- probabilistic model
- machine translation
- language modelling
- query terms
- word clouds
- part of speech
- retrieval model
- ambiguous words
- information extraction
- natural language
- speech recognition
- query expansion
- word error rate
- bilingual dictionaries
- test collection
- statistical language models
- language models for information retrieval
- multiword
- vector space model
- co occurrence
- spoken term detection
- semantic similarity
- statistical machine translation
- document ranking
- feature vectors
- out of vocabulary
- smoothing methods
- context dependent
- term weighting
- computational linguistics
- language processing
- pseudo relevance feedback
- fine tuned
- word level
- machine translation system
- statistical language modeling
- text classification
- document level
- text mining