Comments (2)
Hi xu1998hz,
Sorry for the slow response. I just had time to look into this and I can actually not reproduce the issue. For all 10 systems, we have ratings from 3 different raters for seg id 181. See below bash command:
cat mqm_newstest2020_zhen.tsv | cut -f 1-5 | grep 181 | grep chinanews.com.102535 | sort -u
DeepMind.381 chinanews.com.102535 22 181 rater3
DeepMind.381 chinanews.com.102535 22 181 rater4
DeepMind.381 chinanews.com.102535 22 181 rater6
DiDi_NLP.401 chinanews.com.102535 22 181 rater3
DiDi_NLP.401 chinanews.com.102535 22 181 rater4
DiDi_NLP.401 chinanews.com.102535 22 181 rater6
Human-A.0 chinanews.com.102535 22 181 rater3
Human-A.0 chinanews.com.102535 22 181 rater4
Human-A.0 chinanews.com.102535 22 181 rater6
Human-B.0 chinanews.com.102535 22 181 rater3
Human-B.0 chinanews.com.102535 22 181 rater4
Human-B.0 chinanews.com.102535 22 181 rater6
Huoshan_Translate.919 chinanews.com.102535 22 181 rater3
Huoshan_Translate.919 chinanews.com.102535 22 181 rater4
Huoshan_Translate.919 chinanews.com.102535 22 181 rater6
Online-B.1605 chinanews.com.102535 22 181 rater3
Online-B.1605 chinanews.com.102535 22 181 rater4
Online-B.1605 chinanews.com.102535 22 181 rater6
OPPO.1422 chinanews.com.102535 22 181 rater3
OPPO.1422 chinanews.com.102535 22 181 rater4
OPPO.1422 chinanews.com.102535 22 181 rater6
Tencent_Translation.1249 chinanews.com.102535 22 181 rater3
Tencent_Translation.1249 chinanews.com.102535 22 181 rater4
Tencent_Translation.1249 chinanews.com.102535 22 181 rater6
THUNLP.1498 chinanews.com.102535 22 181 rater3
THUNLP.1498 chinanews.com.102535 22 181 rater4
THUNLP.1498 chinanews.com.102535 22 181 rater6
WeChat_AI.1525 chinanews.com.102535 22 181 rater3
WeChat_AI.1525 chinanews.com.102535 22 181 rater4
WeChat_AI.1525 chinanews.com.102535 22 181 rater6
Let me know if you still see a problem,
Markus
from wmt-mqm-human-evaluation.
Thanks for your response!
from wmt-mqm-human-evaluation.
Related Issues (8)
- Pairwise inter-rater agreement
- [Question]: Is there some way to easily map the source to its reference translation for the Google MQM Dataset? HOT 2
- absent information in the wmt 2020 zhen source errors
- Source-Side Spans HOT 5
- Minor inconsistencies in the data HOT 2
- avg_seg_scores for 2021? HOT 1
- Discrepancy in avg-z scores vs official WMT papers HOT 5
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 wmt-mqm-human-evaluation.