Option for SPECTER2 embeddings?

[japhba]

Hi,

I recently started to use Semantic Scholar's SPECTER2 model to create visualisations of BibTex files. The model is specialised to scientific work, so it seems a good option for the proximity search that searchthearxiv.com offers. While there are gaps in what papers have an associated embedding in their database, its scope extends beyond the ArXiv.

I was thinking to create a service "What was that paper again?" that would

• Take in a description of the user with length of one to ten sentences
• Embed this description using SPECTER2
• Do a proximity search
• Return matching candidates

In summary, the advantages would be

• broader scope beyond ArXiv
• potentially longer queries
• a more accurate backend model

It would be exciting to see this functionality integrated into SearchTheArXiv, I would be very willing to do a prototype!

[augustwester]

Thanks for the suggestion! However, I think this is outside the scope of searchthearxiv.com, which is intentionally low-maintenance, ultra low-cost (i.e. basically free to run), and limited to ML papers. How would searchthearxiv.com differ from Semantic Scholar if we implemented what you describe?