Comments (3)
It's just standard cross-entropy with softmax, over two classes, with the labels corresponding to the positive passages.
So, yes, this is binary classification between the positive and negative examples. Notice this is different from pointwise binary classification (namely, classifying each passage as positive or negative in isolation).
from colbert.
Hi Kyoungrok! Thanks for your question.
For optimization, we treat the task as binary classification between score(query, +ve passage) and score(query, -ve passage). The scores of the positive passages are placed in position zero (and the negatives in position one), hence the labels are all zeros.
from colbert.
Thanks for the answer. As I observe out = (bsize, 2)
and labels = (bsize)
with zeros. Following your explanation If I do F.cross_entropy(out, labels)
then the labels evaluated only on the first column (positive samples) so we have binary classification effect? I think I'm lack of knowledge how this cross_entropy
function works.
from colbert.
Related Issues (20)
- How to index large corpus in mini batches?
- How to setup indexing in docker container HOT 1
- colbert.train FAILED: running distributed training HOT 9
- COLBERTv2 not respond HOT 1
- Regarding about data preparation for ColBERT
- Cannot access pretrained model HOT 6
- Unable to query indexed data, list index out of range HOT 3
- Indexer unable to index with cuda HOT 1
- How to embed and score a query-document-pair? HOT 4
- Explore sharding HOT 5
- Add support for loading ColBERT checkpoint directly from hugging face HOT 2
- Consider uploading to pypi HOT 2
- Fine-Tune ColBERT in Google Colab-Notebook HOT 10
- Clarification about the tokenization process HOT 4
- How to use pre-trained ColBERTv2 checkpoint? HOT 6
- `Example` class loads same chunk of data for every worker? HOT 2
- How to index large corpus which cannot be loaded into the memory? HOT 5
- Using ColBERTv2 for re-ranking HOT 7
- query without passage in collection
- What is faiss actually used for? HOT 1
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.