DE eng

Search in the Catalogues and Directories

Hits 1 – 13 of 13

1
Rule-based Morphological Inflection Improves Neural Terminology Translation ...
BASE
Show details
2
Rule-based Morphological Inflection Improves Neural Terminology Translation ...
Xu, Weijia; Carpuat, Marine. - : arXiv, 2021
BASE
Show details
3
Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer ...
BASE
Show details
4
Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer ...
BASE
Show details
5
Improving Multilingual Neural Machine Translation with Auxiliary Source Languages ...
BASE
Show details
6
How Does Distilled Data Complexity Impact the Quality and Confidence of Non-Autoregressive Machine Translation? ...
BASE
Show details
7
How Does Distilled Data Complexity Impact the Quality and Confidence of Non-Autoregressive Machine Translation? ...
Abstract: Read paper: https://www.aclanthology.org/2021.findings-acl.385 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. ...
Keyword: Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Neural Network; Semantics
URL: https://underline.io/lecture/26476-how-does-distilled-data-complexity-impact-the-quality-and-confidence-of-non-autoregressive-machine-translationquestion
https://dx.doi.org/10.48448/ef4t-3672
BASE
Hide details
8
EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints ...
BASE
Show details
9
A Non-Autoregressive Edit-Based Approach to Controllable Text Simplification ...
BASE
Show details
10
End-to-End Slot Alignment and Recognition for Cross-Lingual NLU ...
BASE
Show details
11
EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraints ...
Xu, Weijia; Carpuat, Marine. - : arXiv, 2020
BASE
Show details
12
Finding stories in the archive through paragraph alignment
In: LLC. - Oxford : Oxford Univ. Press 26 (2011) 3, 359-363
BLLDB
OLC Linguistik
Show details
13
Finding stories in the archive through paragraph alignment
Xu, Weijia; Esteva, Maria. - : Oxford University Press, 2011
BASE
Show details

Catalogues
0
0
1
0
0
0
0
Bibliographies
1
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
12
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern