Now 7779 visitors
Today:0 Yesterday:0
Total: 160209
216S 51P 5R
2026-10-22, Week 43 |
| Member Login |
| TACT Journal Homepage |
| Call for Paper |
| Committee |
| Find My Paper |
| Author Homepage |
| Statistics & History |
| Welcome Message |
| Paper Procedure |
| FAQ |
| Paper Archives |
| Outstanding Papers |
| Author Homepage |
| - Paper Procedure |
| - Journal Procedure |
| - Presentation Tips |
|
| Program & Proceedings |
| Program with Papers |
| Plenary Session |
| Tutorial Session |
|
| Presentation Platform |
| Hotel & Travel Info |
| About Korea |
| Accommodation |
| Transportation |
| VISA |
| Other Infomation |
|
| Photo Gallery |
| Scheduler Login |
| Seminar |
| Archives Login |
|
| Sponsors |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Save Q&A |
 |
* Edit or answer any Q&A by selecting Q&A number Hyper Link below + Write button (Save)
|
ICACT20240321 Question.1
Questioner: maisamali053@gmail.com 2024-02-03 오후 5:33:22 |
ICACT20240321 Answer.1
Answer by Auhor yanghao30@huawei.com 2024-02-03 오후 5:33:22
Chrome  Click!! |
| What are the two primary categories of Machine Translation Quality Estimation (QE), and how is QE formally represented as a function? |
There are two primary categories of Machine Translation Quality Estimation (QE):
Sentence Level Quality Prediction - Predicting the overall quality of a machine translation output without access to reference translations. This is usually framed as a regression or classification task to predict a quality score.
Token Level Quality Prediction - Annotating machine translation output with word or phrase level quality labels, such as OK/BAD tags. This is usually framed as a sequence labeling task. |
ICACT20240321 Question.2
Questioner: htzustc@mail.ustc.edu.cn 2024-02-06 오후 3:36:45 |
ICACT20240321 Answer.2
Answer by Auhor yanghao30@huawei.com 2024-02-06 오후 3:36:45
Chrome Click!! |
| In Slide.10 "CoT Prompt Design", how does the step 4 "Combine the step 1-3 ratings to assign an overall quality estimation" works? What if step 1-3 generate different scores seperately? |
In steps 1-3, 5 scores were generated to evaluate a knowledge prompt. Token-level scores classified tokens as good, acceptable, or bad. Sentence-level scores classified sentences as high, medium or low quality. Perplexity scores measured how uncertain the model was about the prompt. Step 4 aggregated the token, sentence, and perplexity scores into an overall score that correlated well with the individual metrics but was not just their average. The overall score provided a robust evaluation of the knowledge prompt. |
| |
