Comments (4)
Good question! Short answer is that both of our similarity options are identical for ranking. They only differ with a linear transformation during training, but that has no impact on the order/ranking of the passages during retrieval.
Cosine is faster, so we use it consistently in retrieval.
from colbert.
This is a valid choice.
You can train with cosine or L2, both are good although not identical. I think the results are very close.
FAISS uses L2 internally and ranking uses cosine, yes, but that's okay because the vectors are normalized.
from colbert.
Good question! Short answer is that both of our similarity options are identical for ranking. They only differ with a linear transformation during training, but that has no impact on the order/ranking of the passages during retrieval.
Cosine is faster, so we use it consistently in retrieval.
Thanks! So train and rerank both use cosine similarity but index with faiss use L2, is this right?
from colbert.
Closing as this seems resolved. But feel free to re-open if needed.
from colbert.
Related Issues (20)
- Set batch size when indexing HOT 3
- troubleshooting encoding performance HOT 1
- Pre-filtering the documents based on metadata before late-interaction HOT 5
- What is Colbert v1.9?
- Issue: Training "resume" and "resume_optimizer" implementation was removed
- Irrelevant results returned by the Colbert V2 Model HOT 1
- crypt.h: No such file or directory HOT 7
- Basic Training (ColBERTv1-style) -> ujson.JSONDecodeError: Expected object or value HOT 2
- How can I use "all_mpnet_base_v2" model for colbert indexing and searching?
- GPU not working while training a new model in Colab
- [rank1]:[E ProcessGroupNCCL.cpp:523] [Rank 1] Watchdog caught collective operation timeout: WorkNCCL HOT 2
- How to set chunk_size
- Tokens in `skiplist` are not returned (masked out) but they still affect other tokens embeddings. Is this expected? HOT 2
- How to get the mapping information about doc_id with doc_content. HOT 1
- CollectionEncoder blocking on encoder N passages HOT 1
- Focusing retrieval on list of document ids with doc_ids parameter doesn't work
- type object 'ColBERT' has no attribute 'segmented_maxsim' HOT 1
- Where is the qrels.dev.small.tsv?
- How to get rid of the "Duplicate GPU detected : rank 0 and rank 1 both on CUDA device ca000" error while training of the ColBERTv1.9 modell? HOT 1
- Request for AMD gpu support
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from colbert.