Comments (2)
Hi @alvations
Yes, the scores are unbounded for most COMET models (except wmt20-comet-da-qe
that has a sigmoid in the end). Nonetheless, since they are trained to regress on a z-scores they usually range somewhere between -2.5 to 1.2. You can observe that in this plot:
That this plot from WMT20 en-de data which is a high resource and high quality language pair. You can expect this distribution to have a smaller mean for low resource languages.
The max value and min value should be more or less the same because the model does not "risk" much outside those values.
from comet.
Thanks for the explanation! It'll make sense if we somehow distill the model and put a softmax at the final layer so that it spits out [0, 1.0]
.
from comet.
Related Issues (20)
- [QUESTION] Does COMET support Scoring multiple refs like scarebleu? HOT 2
- [QUESTION] How are the older models supposed to be used?
- v1.x and v2.x have different scores for wmt20-comet-qe-da model HOT 2
- [QUESTION]When I train my COMET model, I have the following problem when I am almost successful, it seems to be stuck HOT 2
- Unbabel/wmt22-cometkiwi-da doesn't work from Huggingface HOT 1
- pretrained_model setting in hparams.yaml has no effect HOT 1
- [QUESTION] Why does training speed go down? HOT 5
- Multi-GPU training HOT 10
- Using comet-mbr for Multi-Model Translation Ranking: Questions About Input Format and GPU Disabling HOT 3
- 504 Server error when running comet-score using multiple machines HOT 7
- Is `wmt22-comet-da` the same as "COMET-22" & trained on MQM data? HOT 2
- Quantization HOT 2
- TypeError: comet.models.utils.Prediction is not a dataclasss. This is a subclass of ModelOutput and so must use the @dataclass decorator. HOT 5
- Not compatible with recent transformers? HOT 3
- Comet Evaluation Metric Error with Command line Utility HOT 1
- Running the code on Mac
- whar aspects of language gets considered while evaluating the tranlsation by COMET. as far as I am aware of MQM metric sare covered in it. Interested to know other terminolofy/features of language gets in COMET. HOT 1
- what aspects of language get considered while evaluating the translation by COMET. as far as I am aware of MQM metrics are covered in it. Interested in knowing other terminology/features of language gets in COMET. I am looking for metric along with COMET that can assess the translated content for cosmetic domain data. please suggest. HOT 1
- [QUESTION] Train Your Own Metric HOT 2
- Multi-gpu inference returns AttributeError HOT 7
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 comet.