DE eng

Search in the Catalogues and Directories

Page: 1 2
Hits 1 – 20 of 31

1
Graph Algorithms for Multiparallel Word Alignment
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing ; The 2021 Conference on Empirical Methods in Natural Language Processing ; https://hal.archives-ouvertes.fr/hal-03424044 ; The 2021 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Nov 2021, Punta Cana, Dominica ; https://2021.emnlp.org/ (2021)
BASE
Show details
2
Static Embeddings as Efficient Knowledge Bases? ...
BASE
Show details
3
ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpus ...
BASE
Show details
4
Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models ...
BASE
Show details
5
Wine is Not v i n. -- On the Compatibility of Tokenizations Across Languages ...
BASE
Show details
6
Graph Algorithms for Multiparallel Word Alignment ...
BASE
Show details
7
Locating Language-Specific Information in Contextualized Embeddings ...
BASE
Show details
8
Static Embeddings as Efficient Knowledge Bases? ...
NAACL 2021 2021; Dufter, Philipp; Kassner, Nora. - : Underline Science Inc., 2021
BASE
Show details
9
ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpus ...
BASE
Show details
10
SimAlign: High Quality Word Alignments Without Parallel Training Data Using Static and Contextualized Embeddings
In: EMNLP 2020 ; https://hal.archives-ouvertes.fr/hal-03013194 ; EMNLP 2020, Association for Computational Linguistics, Nov 2020, Online, United States. pp.1627 - 1643 (2020)
BASE
Show details
11
Identifying Necessary Elements for BERT’s Multilinguality
Abstract: It has been shown that multilingual BERT (mBERT) yields high quality multilingual rep- resentations and enables effective zero-shot transfer. This is suprising given that mBERT does not use any kind of crosslingual sig- nal during training. While recent literature has studied this effect, the exact reason for mBERT’s multilinguality is still unknown. We aim to identify architectural properties of BERT as well as linguistic properties of lan- guages that are necessary for BERT to become multilingual. To allow for fast experimenta- tion we propose an efficient setup with small BERT models and synthetic as well as natu- ral data. Overall, we identify six elements that are potentially necessary for BERT to be mul- tilingual. Architectural factors that contribute to multilinguality are underparameterization, shared special tokens (e.g., “[CLS]”), shared position embeddings and replacing masked to- kens with random tokens. Factors related to training data that are beneficial for multilin- guality are similar word order and comparabil- ity of corpora.
Keyword: ddc:000; ddc:410
URL: https://epub.ub.uni-muenchen.de/72199/
https://epub.ub.uni-muenchen.de/72199/1/identify,dufter.pdf
https://doi.org/10.5282/ubm/epub.72199
http://nbn-resolving.de/urn:nbn:de:bvb:19-epub-72199-8
BASE
Hide details
12
Identifying Elements Essential for BERT’s Multilinguality
BASE
Show details
13
SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings
In: Findings of ACL: EMNLP 2020 (2020)
BASE
Show details
14
Monolingual and Multilingual Reduction of Gender Bias in Contextualized Representations
BASE
Show details
15
Increasing Learning Efficiency of Self-Attention Networks through Direct Position Interactions, Learnable Temperature, and Convoluted Attention
BASE
Show details
16
SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings ...
BASE
Show details
17
Identifying Necessary Elements for BERT's Multilinguality ...
BASE
Show details
18
Identifying Elements Essential for BERT’s Multilinguality ...
Dufter, Philipp; Schütze, Hinrich. - : Universitätsbibliothek der Ludwig-Maximilians-Universität München, 2020
BASE
Show details
19
Identifying Necessary Elements for BERT’s Multilinguality ...
Dufter, Philipp; Schütze, Hinrich. - : Universitätsbibliothek der Ludwig-Maximilians-Universität München, 2020
BASE
Show details
20
Monolingual and Multilingual Reduction of Gender Bias in Contextualized Representations ...
Liang, Sheng; Dufter, Philipp; Schütze, Hinrich. - : Universitätsbibliothek der Ludwig-Maximilians-Universität München, 2020
BASE
Show details

Page: 1 2

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
31
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern