Comments (6)
Hi @gm0616,
Actually, the code is almost exactly the same, with a couple of additional short scripts. To start, you just need to split the long documents into passages and create triples for supervision. "MaxP" just means MaxPassage, that is, we assign each document the score of its highest-scoring passage.
I agree releasing the extra instructions and scripts will be useful for others. I will update here on this.
from colbert.
Thanks for a detailed reply. I probably got the idea of the process.
To start, you just need to split the long documents into passages and create triples for supervision.
And what are your experiment settings here?
- maximum length of the passage?
- doc stride?
- how to get triplets? Are all other passages are used as negative samples, or just a few passages are sampled as hard negatives?
from colbert.
The maximum length was 450 BERT tokens. I applied no hyperparameter tuning over this, however, so it's possible that other choices work too. The doc stride was also untuned. For this long-document task, I think it's around 60 BERT tokens, irrc.
To get initial training triples, we use zero-shot transfer of ColBERT trained on the passage task of MS MARCO. I suspect you can also start from BM25. We then divide the top-1000 passages retrieved into buckets: positive, negative, ignored. Negatives are passages that come from negative documents, positives are the best (one or more) passages that come from the positive document, and the rest are ignored (they are technically very weak positives; hence, not used in training).
from colbert.
Thank you for the fast response! The method of constructing triplets sounds like a great idea, I will try that as well. Thanks!!
from colbert.
By the way, let me know if you need the ColBERT ranking output on this task (e.g., if you'd like to re-rank it). We're happy to share/release it.
from colbert.
I think it's around 60 BERT tokens
I wonder whether using a sliding window technique in any way hinder the retrieval of lower rank documents.
In a sliding window implementation, the same token will appear in multiple segments. So during retrieval, in the first stage, among all the top k' token embeddings, many will essentially be a slight variation of the same token. This in essence would prevent the tokens from other documents from being retrieved.
Is this something one needs to be wary of, @okhat?
from colbert.
Related Issues (20)
- 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
- How to quickly check if installation is working fine?
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.