TE
TechEcho
StartseiteTop 24hNeuesteBesteFragenZeigenJobs
GitHubTwitter
Startseite

TechEcho

Eine mit Next.js erstellte Technologie-Nachrichtenplattform, die globale Technologienachrichten und Diskussionen bietet.

GitHubTwitter

Startseite

StartseiteNeuesteBesteFragenZeigenJobs

Ressourcen

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. Alle Rechte vorbehalten.

Bridging the gap between keyword and semantic search with SPLADE (2024)

21 Punktevon softwaredougvor 3 Tagen

1 comment

jbellisvor etwa 7 Stunden
I&#x27;m kind of disappointed in this article, Splade is a cool way to improve results of a TF&#x2F;IDF index with minimally invasive changes and this obscures that more than it clarifies.<p>&gt; Next, my SPLADE implementation in Elasticsearch is oversimplified. If you scroll back up to get_splade_embedding, we extract non-zero elements from vec_np (the SPLADE tokens) but discard their associated weights. This is a missed opportunity. The SPLADE papers use these weights for scoring matches.<p>Yes, exactly, that is the whole point of Splade.<p>Probably easier to demonstrate if you drop down a level to Lucene, I don&#x27;t think you will be able to do it easily with Elastic.<p>Tangentially, I haven&#x27;t looked closely at SPLATE which tries to marry Splade and ColBERT, but it&#x27;s an interesting idea. <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;html&#x2F;2404.13950v1" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;html&#x2F;2404.13950v1</a>
评论 #43927241 未加载