@prefix rdf:   <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
@prefix sl:    <http://www.semanlink.net/2001/00/semanlink-schema#> .
@prefix skos:  <http://www.w3.org/2004/02/skos/core#> .
@prefix rdfs:  <http://www.w3.org/2000/01/rdf-schema#> .
@prefix tag:   <http://www.semanlink.net/tag/> .
@prefix foaf:  <http://xmlns.com/foaf/0.1/> .
@prefix dc:    <http://purl.org/dc/elements/1.1/> .

<http://www.semanlink.net/doc/2022/10/nils_reimers_sur_twitter_mte>
        dc:title         "Nils Reimers sur Twitter : \"MTEB - Massive Text Embedding Benchmark ...\"" ;
        sl:creationDate  "2022-10-17" ;
        sl:tag           tag:tweet , tag:text_embeddings , tag:nils_reimers , tag:mteb , tag:benchmark .

<http://www.semanlink.net/doc/2022/10/2210_07316_mteb_massive_text>
        dc:title         "[2210.07316] MTEB: Massive Text Embedding Benchmark" ;
        sl:comment       "> It is unclear whether state-of-the-art embeddings on semantic textual similarity (STS) can be equally well applied to other tasks like clustering or reranking. This makes progress in the field difficult to track, as various models are constantly being proposed without proper evaluation. To solve this problem, we introduce MTEB\r\n\r\n[Leaderbord](https://huggingface.co/spaces/mteb/leaderboard)" ;
        sl:creationDate  "2022-10-17" ;
        sl:tag           tag:text_embeddings , tag:nils_reimers , tag:mteb , tag:arxiv_doc .

tag:mteb  a               sl:Tag ;
        rdfs:isDefinedBy  tag:mteb.n3 ;
        skos:broader      tag:text_embeddings , tag:benchmark ;
        skos:prefLabel    "MTEB" ;
        skos:related      tag:nils_reimers ;
        foaf:page         tag:mteb.html .

tag:text_embeddings  a  sl:Tag ;
        skos:prefLabel  "Text Embeddings" .

tag:knowledge_distillation
        a               sl:Tag ;
        skos:prefLabel  "Knowledge distillation" .

tag:nils_reimers  a     sl:Tag ;
        skos:prefLabel  "Nils Reimers" .

tag:tweet  a            sl:Tag ;
        skos:prefLabel  "Tweet" .

tag:benchmark  a        sl:Tag ;
        skos:prefLabel  "Benchmark" .

<http://www.semanlink.net/doc/2025/01/benjamin_clavie_sur_x_%F0%9F%A7%B5_ste>
        dc:title         "Benjamin Clavié sur X : \"Stella Embeddings: What's the big deal?...\"" ;
        sl:comment       "> Training based on unsupervised distillation\r\n\r\n> The current dominant way of training retrieval models is via the use of a contrastive loss, with little-to-no knowledge distillation\r\n> (Stella's) training work within the embedding space, seeking to minimize the geometric distances... between the teachers' vectors and the student model (Stella)'s outputs.\r\n> \r\n> Stella models (and Jasper models) generalize amazingly well because of this.\r\n" ;
        sl:creationDate  "2025-01-13" ;
        sl:tag           tag:text_embeddings , tag:mteb , tag:knowledge_distillation , tag:benjamin_clavie .

tag:benjamin_clavie  a  sl:Tag ;
        skos:prefLabel  "Benjamin Clavié" .

tag:arxiv_doc  a        sl:Tag ;
        skos:prefLabel  "Arxiv Doc" .