DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4 5...59
Hits 1 – 20 of 1.168

1
Characterizing News Portrayal of Civil Unrest in Hong Kong, 1998–2020 ...
BASE
Show details
2
Jibes & Delights: A Dataset of Targeted Insults and Compliments to Tackle Online Abuse​ ...
BASE
Show details
3
Bird’s Eye: Probing for Linguistic Graph Structures with a Simple Information-Theoretic Approach ...
BASE
Show details
4
10D: Phonology, Morphology and Word Segmentation #1 ...
BASE
Show details
5
Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems ...
BASE
Show details
6
19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology - Part 2 ...
BASE
Show details
7
18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology - Part 1 ...
BASE
Show details
8
The Match-Extend Serialization Algorithm in Multiprecedence ...
BASE
Show details
9
Recognizing Reduplicated Forms: Finite-State Buffered Machines ...
BASE
Show details
10
Correcting Chinese Spelling Errors with Phonetic Pre-training ...
BASE
Show details
11
PLOME: Pre-training with Misspelled Knowledge for Chinese Spelling Correction ...
BASE
Show details
12
Including Signed Languages in Natural Language Processing ...
BASE
Show details
13
When is Char Better Than Subword: A Systematic Study of Segmentation Algorithms for Neural Machine Translation ...
Abstract: Read paper: https://www.aclanthology.org/2021.acl-short.69 Abstract: Subword segmentation algorithms have been a \textit{de facto} choice when building neural machine translation systems. However, most of them need to learn a segmentation model based on some heuristics, which may produce sub-optimal segmentation. This can be problematic in some scenarios when the target language has rich morphological changes or there is not enough data for learning compact composition rules. Translating at fully character level has the potential to alleviate the issue, but empirical performances of character-based models has not been fully explored. In this paper, we present an in-depth comparison between character-based and subword-based NMT systems under three settings: translating to typologically diverse languages, training with low resource, and adapting to unseen domains. Experiment results show strong competitiveness of character-based models. Further analyses show that compared to subword-based models, ...
Keyword: Computational Linguistics; Condensed Matter Physics; Deep Learning; Electromagnetism; FOS Physical sciences; Information and Knowledge Engineering; Neural Network; Semantics
URL: https://dx.doi.org/10.48448/mz1t-5939
https://underline.io/lecture/25626-when-is-char-better-than-subword-a-systematic-study-of-segmentation-algorithms-for-neural-machine-translation
BASE
Hide details
14
The Reading Machine: a Versatile Framework for Studying Incremental Parsing Strategies ...
BASE
Show details
15
To POS Tag or Not to POS Tag: The Impact of POS Tags on Morphological Learning in Low-Resource Settings ...
BASE
Show details
16
Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words ...
BASE
Show details
17
LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification ...
BASE
Show details
18
Quotation Recommendation and Interpretation Based on Transformation from Queries to Quotations ...
BASE
Show details
19
How Did This Get Funded?! Automatically Identifying Quirky Scientific Achievements ...
BASE
Show details
20
Minimax and Neyman–Pearson Meta-Learning for Outlier Languages ...
BASE
Show details

Page: 1 2 3 4 5...59

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
1.168
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern