2 |
Rule-based Morphological Inflection Improves Neural Terminology Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Rule-based Morphological Inflection Improves Neural Terminology Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Evaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Beyond Noise: Mitigating the Impact of Fine-grained Semantic Divergences on Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
The UMD Submission to the Explainable MT Quality Estimation Shared Task: Combining Explanation Models with Sequence Labeling ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Evaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
How Does Distilled Data Complexity Impact the Quality and Confidence of Non-Autoregressive Machine Translation? ...
|
|
|
|
Abstract:
While non-autoregressive (NAR) models are showing great promise for machine translation, their use is limited by their dependence on knowledge distillation from autoregressive models. To address this issue, we seek to understand why distillation is so effective. Prior work suggests that distilled training data is less complex than manual translations. Based on experiments with the Levenshtein Transformer and the Mask-Predict NAR models on the WMT14 German-English task, this paper shows that different types of complexity have different impacts: while reducing lexical diversity and decreasing reordering complexity both help NAR learn better alignment between source and target, and thus improve translation quality, lexical diversity is the main reason why distillation increases model confidence, which affects the calibration of different NAR models differently. ... : Findings of ACL 2021 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2105.12900 https://dx.doi.org/10.48550/arxiv.2105.12900
|
|
BASE
|
|
Hide details
|
|
9 |
EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
A Non-Autoregressive Edit-Based Approach to Controllable Text Simplification ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to Rank ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Incorporating Terminology Constraints in Automatic Post-Editing ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Controlling Neural Machine Translation Formality with Synthetic Supervision ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Controlling Text Complexity in Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Formality Style Transfer Within and Across Languages with Limited Supervision
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Identifying Semantic Divergences in Parallel Text without Annotations ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Bi-Directional Neural Machine Translation with Synthetic Parallel Data ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Multi-Task Neural Models for Translating Between Styles Within and Across Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|