JetBrains-Research / pubtrends

Scientific literature explorer. Runs a Pubmed or Semantic Scholar search and allows user to explore high-level structure of result papers
Apache License 2.0
35 stars 2 forks source link

Use pre-trained fast-text embeddings for texts vectorisation #301

Closed olegs closed 2 years ago

olegs commented 2 years ago

Alternatively, we can use pertained model and train it additionally on Semantic Scholar dataset to improve science texts embeddings.

olegs commented 2 years ago

Implemented in https://github.com/JetBrains-Research/pubtrends/commit/e4597630bed54b54b31be986dc715679342dc6c4