DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4 5 6 7 8...60
Hits 61 – 80 of 1.194

61
Structural Arrangement of Simple Semantically Elementary Constructions ...
Masytska, Tetiana; Vaseiko, Yulia. - : Zenodo, 2020
BASE
Show details
62
On understanding character-level models for representing morphology ...
Vania, Clara. - : The University of Edinburgh, 2020
BASE
Show details
63
Word order preferences and the effect of phrasal length in SOV languages: evidence from sentence production in Persian
In: Glossa: a journal of general linguistics; Vol 5, No 1 (2020); 86 ; 2397-1835 (2020)
BASE
Show details
64
Automatic Pronoun Resolution for Swedish ; Automatisk pronomenbestämning på svenska
Ahlenius, Camilla. - : KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020
BASE
Show details
65
Open Challenges on Generating Referring Expressions for Human-Robot Interaction
Leite, Iolanda; Dogan, Fethiye Irmak. - : KTH, Robotik, perception och lärande, RPL, 2020
BASE
Show details
66
Теорія залежностей у сучасному синтаксисі ; The theory of dependency in contemporary syntax ; Теория зависимостей в современном синтаксисе
BASE
Show details
67
Dependency Treebanks of Ancient Greek Prose
In: Journal of Open Humanities Data; Vol 6 (2020); 1 ; 2059-481X (2020)
BASE
Show details
68
LanguageStructure/TuDeT v0.1 ...
BASE
Show details
69
Linguatec Tolosa Treebank ...
BASE
Show details
70
Linguatec Tolosa Treebank ...
BASE
Show details
71
LanguageStructure/TuDeT v0.1 ...
BASE
Show details
72
Word order preferences and the effect of phrasal length in SOV languages: evidence from sentence production in Persian
In: Glossa: a journal of general linguistics (2016-2021) ; https://hal.archives-ouvertes.fr/hal-02559840 ; Glossa: a journal of general linguistics (2016-2021), Ubiquity Press, 2020, 5 (1), pp.86. ⟨10.5334/gjgl.1078⟩ (2020)
BASE
Show details
73
Demographic-Aware Natural Language Processing
BASE
Show details
74
Top-Down Grouping Affects Adjacent Dependency Learning
In: Psychology Faculty Publications (2020)
BASE
Show details
75
On understanding character-level models for representing morphology
Vania, Clara. - : The University of Edinburgh, 2020
Abstract: Morphology is the study of how words are composed of smaller units of meaning (morphemes). It allows humans to create, memorize, and understand words in their language. To process and understand human languages, we expect our computational models to also learn morphology. Recent advances in neural network models provide us with models that compose word representations from smaller units like word segments, character n-grams, or characters. These so-called subword unit models do not explicitly model morphology yet they achieve impressive performance across many multilingual NLP tasks, especially on languages with complex morphological processes. This thesis aims to shed light on the following questions: (1) What do subword unit models learn about morphology? (2) Do we still need prior knowledge about morphology? (3) How do subword unit models interact with morphological typology? First, we systematically compare various subword unit models and study their performance across language typologies. We show that models based on characters are particularly effective because they learn orthographic regularities which are consistent with morphology. To understand which aspects of morphology are not captured by these models, we compare them with an oracle with access to explicit morphological analysis. We show that in the case of dependency parsing, character-level models are still poor in representing words with ambiguous analyses. We then demonstrate how explicit modeling of morphology is helpful in such cases. Finally, we study how character-level models perform in low resource, cross-lingual NLP scenarios, whether they can facilitate cross-linguistic transfer of morphology across related languages. While we show that cross-lingual character-level models can improve low-resource NLP performance, our analysis suggests that it is mostly because of the structural similarities between languages and we do not yet find any strong evidence of crosslinguistic transfer of morphology. This thesis presents a careful, in-depth study and analyses of character-level models and their relation to morphology, providing insights and future research directions on building morphologically-aware computational NLP models.
Keyword: character-level models; dependency parsing; morphemes; morphology; natural language processing; NLP
URL: https://doi.org/10.7488/era/49
https://hdl.handle.net/1842/36742
BASE
Hide details
76
Studying Dependency Maintenance Practices Through the Mining of Data from npm Packages
Cogo, Filipe. - 2020
BASE
Show details
77
Cognitive Constraints Built into Formal Grammars: Implications for Language Evolution
Gómez-Rodríguez, Carlos; Christiansen, Morten H.; Ferrer-i-Cancho, Ramon. - : Ravignani, A., Barbieri, C., Martins, M., Flaherty, M., Jadoul, Y., Lattenkamp, E., Little, H., Mudd, K., Verhoef, T., 2020
BASE
Show details
78
The structural motivation of palatalization ; A motivação estrutural da palatalização ; La motivación estructural de la palatalización
BASE
Show details
79
Self attended stack pointer networks for learning long term dependencies
Can, Burcu; Tuç, Salih. - : Association for Computational Linguistics, 2020
BASE
Show details
80
Induction of Minimalist Grammars over Morphemes
In: Proceedings of the Society for Computation in Linguistics (2020)
BASE
Show details

Page: 1 2 3 4 5 6 7 8...60

Catalogues
108
58
43
0
7
8
17
Bibliographies
405
3
59
0
0
0
0
16
7
Linked Open Data catalogues
0
Online resources
11
0
0
0
Open access documents
586
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern