Cherche: A Neural Search Pipeline

January 10, 2022

For fans of open source search, Cherche is available. The GitHub write up states:

Cherche is meant to be used with small to medium sized corpora. Cherche’s main strength is its ability to build diverse and end-to-end pipelines.

The “neural search” module includes ElasticSearch. The programming team for Cherche consists of Raphaël Sourty and François-Paul Servant. Beyond Search has not fired up the system and run it against our test corpus. We did have in our files a paper called “Knowledge Base Embedding by Cooperative Knowledge Distillation.” That paper states:

Given a set of KBs, our proposed approach KDMKB, learns KB embeddings by mutually and jointly distilling knowledge within a dynamic teacher-student setting. Experimental results on two standard datasets show that knowledge distillation between KBs through entity and relation inference is actually observed. We also show that cooperative learning significantly outperforms the two proposed baselines, namely traditional and sequential distillation.

The idea is that instead of retrieving strings, broader tags (concepts and classifications) appear to provide an advantage; pushing “beyond” old school search.

Stephen E Arnold, January 10, 2022

Comments

Got something to say?





  • Archives

  • Recent Posts

  • Meta