ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT · HackerPapers discussions

ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT — mentioned by tadkar

Fri, 24 Jan 2025 06:44:01 GMT

Here’s my understanding. It is intimidating to write a response to you, because you have an exceptionally clear writing style. I hope the more knowledgable HN crowd will correct any errors in fact or presentation style below. Old school word embedding models (like Word2Vec) come up with embeddings by using masked word predictions. You can embed a whole sentence by taking the average of all the word embeddings in the sentence. There are many scenarios where this average fails to distinguish between multiple meanings of a word. For example “fine weather” and “fine hair” both contain “fine” but…

Paper and discussion history. A mention is not an endorsement.

ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT — mentioned by will-burner

Fri, 20 Sep 2024 15:52:11 GMT

This is an interesting development. A couple blog posts exposing on late chunking https://weaviate.io/blog/late-chunking https://jina.ai/news/late-chunking-in-long-context-embedding... The late chunking idea originates from ColBERT, an embedding technique from 2020 https://arxiv.org/pdf/2004.12832

Paper and discussion history. A mention is not an endorsement.

ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT — mentioned by jbellis

Wed, 29 May 2024 22:46:05 GMT

ColBERT gives you best of both worlds. https://arxiv.org/abs/2004.12832 https://thenewstack.io/overcoming-the-limits-of-rag-with-col...

Paper and discussion history. A mention is not an endorsement.

ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT — HN submission

Thu, 04 Jan 2024 16:48:34 GMT

Show HN: RAGatouille, a simple lib to use&train top retrieval models in RAG apps

Hey HN! If you’re at all interested in LLMs/LLM-apps, you’ve probably heard of RAG: Retrieval-Assisted Generation, i.e. retrieving relevant documents to give to your LLM as context to answer user queries. Today, I’m releasing RAGatouille v0.0.1, whose aim is to make it as easy as can be to improve your RAG pipelines by leveraging state-of-the-art Information Retrieval research. As of right now, there’s quite a big gap between common everyday practice and the IR literature, and a lot of the gap is because there just aren’t good ways to quickly try out and leverage SotA IR techniques.…

15 points; 5 discussion replies on HN. Paper and source history. A submission is not an endorsement.