DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4 5 6 7 8 9...149
Hits 81 – 100 of 2.974

81
Data for: Psycholinguistic dataset on language use in 1145 novels published in English and Dutch ...
Van Cranenburgh, Andreas. - : Mendeley, 2021
BASE
Show details
82
Graph-to-Graph Translations To Augment Abstract Meaning Representation Tense And Aspect ...
Bakal, Mollie. - : My University, 2021
BASE
Show details
83
A Journey in Linguistic Computing from Father Busa to Linguistic Linked Data ...
Passarotti, Marco. - : Zenodo, 2021
BASE
Show details
84
A Journey in Linguistic Computing from Father Busa to Linguistic Linked Data ...
Passarotti, Marco. - : Zenodo, 2021
BASE
Show details
85
Signed Coreference Resolution ...
BASE
Show details
86
Including Signed Languages in Natural Language Processing ...
BASE
Show details
87
Key to BibleWorks Greek Morphology (BGM) ...
Bilby, Mark Glen. - : Zenodo, 2021
BASE
Show details
88
Key to BibleWorks Greek Morphology (BGM) ...
Bilby, Mark Glen. - : Zenodo, 2021
BASE
Show details
89
Backtranslation in Neural Morphological Inflection ...
BASE
Show details
90
Rule-based Morphological Inflection Improves Neural Terminology Translation ...
BASE
Show details
91
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
92
The Reading Machine: a Versatile Framework for Studying Incremental Parsing Strategies ...
BASE
Show details
93
To POS Tag or Not to POS Tag: The Impact of POS Tags on Morphological Learning in Low-Resource Settings ...
BASE
Show details
94
Translating Headers of Tabular Data: A Pilot Study of Schema Translation ...
BASE
Show details
95
A Prototype Free/Open-Source Morphological Analyser and Generator for Sakha ...
BASE
Show details
96
Automatic Error Type Annotation for Arabic ...
BASE
Show details
97
Developing Conversational Data and Detection of Conversational Humor in Telugu ...
BASE
Show details
98
Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words ...
BASE
Show details
99
HIT - A Hierarchically Fused Deep Attention Network for Robust Code-mixed Language Representation ...
BASE
Show details
100
Minimally-Supervised Morphological Segmentation using Adaptor Grammars with Linguistic Priors ...
BASE
Show details

Page: 1 2 3 4 5 6 7 8 9...149

Catalogues
0
0
0
0
0
0
3
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
2.971
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern