Improving Low Compute Language Modeling with In-Domain Embedding Initialisation.
Charles WelchRada MihalceaJonathan K. KummerfeldPublished in: EMNLP (1) (2020)
Keyphrases
- language modeling
- language model
- information retrieval
- n gram
- retrieval model
- query expansion
- cross lingual
- probabilistic model
- statistical language models
- relevance model
- text classification
- vector space
- sentence retrieval
- translation model
- language modeling approaches
- trec collections
- data mining
- document retrieval
- test collection
- mixture model
- digital libraries