1 |
Knowledge Distillation for Quality Estimation ...
|
|
|
|
Abstract:
Quality Estimation (QE) is the task of automatically predicting Machine Translation quality in the absence of reference translations, making it applicable in real-time settings, such as translating online social media conversations. Recent success in QE stems from the use of multilingual pre-trained representations, where very large models lead to impressive results. However, the inference time, disk and memory requirements of such models do not allow for wide usage in the real world. Models trained on distilled pre-trained representations remain prohibitively large for many usage scenarios. We instead propose to directly transfer knowledge from a strong QE teacher model to a much smaller model with a different, shallower architecture. We show that this approach, in combination with data augmentation, leads to light-weight QE models that perform competitively with distilled pre-trained representations with 8x fewer parameters. ... : ACL Findings 2021 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2107.00411 https://arxiv.org/abs/2107.00411
|
|
BASE
|
|
Hide details
|
|
3 |
Controllable Text Simplification with Explicit Paraphrasing ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
The (Un)Suitability of Automatic Evaluation Metrics for Text Simplification ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
deepQuest-py: large and distilled models for quality estimation
|
|
|
|
BASE
|
|
Show details
|
|
7 |
IAPUCP at SemEval-2021 task 1: Stacking fine-tuned transformers is almost all you need for lexical complexity prediction
|
|
|
|
BASE
|
|
Show details
|
|
8 |
The (un)suitability of automatic evaluation metrics for text simplification
|
|
|
|
BASE
|
|
Show details
|
|
10 |
deepQuest-py: large and distilled models for quality estimation
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations ; 382 ; 389 (2021)
|
|
BASE
|
|
Show details
|
|
11 |
Knowledge distillation for quality estimation
|
|
|
|
In: 5091 ; 5099 (2021)
|
|
BASE
|
|
Show details
|
|
12 |
ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations
|
|
|
|
In: ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics ; https://hal.inria.fr/hal-02889823 ; ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Jul 2020, Seattle / Virtual, United States (2020)
|
|
BASE
|
|
Show details
|
|
13 |
Controllable Text Simplification with Explicit Paraphrasing ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
ASSET: A dataset for tuning and evaluation of sentence simplification models with multiple rewriting transformations
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Data-Driven Sentence Simplification: Survey and Benchmark
|
|
|
|
In: Computational Linguistics, Vol 46, Iss 1, Pp 135-187 (2020) (2020)
|
|
BASE
|
|
Show details
|
|
17 |
Automatic Sentence Simplification with Multiple Rewriting Transformations
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Distributed knowledge based clinical auto-coding system
|
|
Kaur, Rajvir (S33301). - : U.S., Association for Computational Linguistics, 2019
|
|
BASE
|
|
Show details
|
|
19 |
Towards semi-supervised Brazilian Portuguese semantic role labeling: Building a benchmark
|
|
|
|
BASE
|
|
Show details
|
|
|
|