DE eng

Search in the Catalogues and Directories

Hits 1 – 19 of 19

1
Towards Zero-shot Language Modeling ...
Abstract: Can we construct a neural model that is inductively biased towards learning human languages? Motivated by this question, we aim at constructing an informative prior over neural weights, in order to adapt quickly to held-out languages in the task of character-level language modeling. We infer this distribution from a sample of typologically diverse training languages via Laplace approximation. The use of such a prior outperforms baseline models with an uninformative prior (so-called "fine-tuning") in both zero-shot and few-shot settings. This shows that the prior is imbued with universal phonological knowledge. Moreover, we harness additional language-specific side information as distant supervision for held-out languages. Specifically, we condition language models on features from typological databases, by concatenating them to hidden states or generating weights with hyper-networks. These features appear beneficial in the few-shot setting, but not in the zero-shot setting. Since the paucity of digital texts ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences
URL: https://arxiv.org/abs/2108.03334
https://dx.doi.org/10.48550/arxiv.2108.03334
BASE
Hide details
2
Parameter space factorization for zero-shot learning across tasks and languages ...
BASE
Show details
3
Parameter space factorization for zero-shot learning across tasks and languages
In: Transactions of the Association for Computational Linguistics, 9 (2021)
BASE
Show details
4
A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters ...
BASE
Show details
5
A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters ...
BASE
Show details
6
Multi-SimLex: A Large-Scale Evaluation of Multilingual and Cross-Lingual Lexical Semantic Similarity ...
BASE
Show details
7
The Secret is in the Spectra: Predicting Cross-lingual Task Performance with Spectral Similarity Measures ...
BASE
Show details
8
Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing
In: ISSN: 0891-2017 ; EISSN: 1530-9312 ; Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-02425462 ; Computational Linguistics, Massachusetts Institute of Technology Press (MIT Press), 2019, 45 (3), pp.559-601. ⟨10.1162/coli_a_00357⟩ ; https://www.mitpressjournals.org/doi/abs/10.1162/coli_a_00357 (2019)
BASE
Show details
9
Do We Really Need Fully Unsupervised Cross-Lingual Embeddings? ...
BASE
Show details
10
Cross-lingual semantic specialization via lexical relation induction
Glavaš, Goran; Vulić, Ivan; Korhonen, Anna. - : Association for Computational Linguistics, 2019
BASE
Show details
11
Do we really need fully unsupervised cross-lingual embeddings?
Vulić, Ivan; Glavaš, Goran; Reichart, Roi. - : Association for Computational Linguistics, 2019
BASE
Show details
12
Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing
In: Computational Linguistics, Vol 45, Iss 3, Pp 559-601 (2019) (2019)
BASE
Show details
13
Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing ...
BASE
Show details
14
Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints ...
BASE
Show details
15
Morph-fitting: Fine-Tuning Word Vector Spaces with Simple Language-Specific Rules ...
BASE
Show details
16
Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints ...
Mrkšić, Nikola; Vulić, Ivan; Ó Séaghdha, Diarmuid. - : Apollo - University of Cambridge Repository, 2017
BASE
Show details
17
Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints
Mrkšić, Nikola; Vulić, Ivan; Ó Séaghdha, Diarmuid. - : Association for Computational Linguistics, 2017. : https://www.transacl.org/ojs/index.php/tacl/article/view/1171, 2017. : Transactions of the Association for Computational Linguistics (TACL), 2017
BASE
Show details
18
Survey on the Use of Typological Information in Natural Language Processing ...
BASE
Show details
19
Automatic Selection of Context Configurations for Improved Class-Specific Word Representations ...
BASE
Show details

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
19
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern