Comments (3)
Thanks! I wasn't aware.
For future reference:
Instead of averaging the sentence level BLEU scores (i.e. marco-average precision), the original BLEU metric (Papineni et al. 2002) accounts for the micro-average precision (i.e. summing the numerators and denominators for each hypothesis-reference(s) pairs before the division).
from nlg-eval.
This is expected behavior. BLEU and METEOR are calculated across the entire corpus and the corpus score is not supposed to be the average of sentence scores. You can search online for corpus BLEU
and you will find several explanations available.
from nlg-eval.
This was the reason behind why this repository originally assumed that you would have all the hypothesis and references in advance and then you would run compute_metrics
over them to report the corpus level scores as most papers just report that.
from nlg-eval.
Related Issues (20)
- Getting " Unknown parameter type " on model instantiation HOT 3
- Add metrics to compute fluency of references HOT 6
- Getting error "ValueError: could not convert string to float: '' HOT 2
- Why do I only output Bleu when I use it on Mac ?
- download for glove 6B fails HOT 3
- ModuleNotFoundError: No module named 'nlgeval' HOT 7
- Problem with "the object oriented API for repeated calls in a script - multiple examples" HOT 4
- _pickle.UnpicklingError: pickle data was truncated HOT 1
- zipfile.BadZipFile: File is not a zip file
- TypeError: compute_individual_metrics() missing 1 required positional argument: 'hyp' HOT 2
- Assertion Error HOT 1
- about the files downloaded HOT 1
- nlg-eval --setup
- BrokenPipeError HOT 1
- CIDEr score evaluates to 0.0 no matter what references and metrics I use
- thanks for the codes! I have a question: should I tokenize the predictions and reference texts before using this api? HOT 1
- nlg-eval --setup error can't download glove.6B.zip HOT 3
- Compatibility with gensim 4 HOT 1
- New releases? HOT 1
- v2.4.0 tag does not have the right version info 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 nlg-eval.