4 |
WALS Online Resources for Swedish (Västerbotten)
|
|
: Max Planck Institute for Evolutionary Anthropology, 2021
|
|
BASE
|
|
Show details
|
|
5 |
WALS Online Resources for Swedish
|
|
: Max Planck Institute for Evolutionary Anthropology, 2021
|
|
BASE
|
|
Show details
|
|
6 |
Glottolog 4.4 Resources for Swedish
|
|
: Max Planck Institute for Evolutionary Anthropology, 2021
|
|
BASE
|
|
Show details
|
|
7 |
Interconnected literacy practices. Exploring classroom work with literature in adult second language education ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Continuity and change. Migrants' experiences of adult language education in Sweden ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
AfBo: A world-wide survey of affix borrowing Resources for Swedish
|
|
: Max Planck Institute for Evolutionary Anthropology, 2020
|
|
BASE
|
|
Show details
|
|
11 |
Interconnected literacy practices. Exploring classroom work with literature in adult second language education
|
|
|
|
In: European journal for Research on the Education and Learning of Adults 11 (2020) 1, S. 45-63 (2020)
|
|
BASE
|
|
Show details
|
|
12 |
Continuity and change. Migrants' experiences of adult language education in Sweden
|
|
|
|
In: European journal for Research on the Education and Learning of Adults 11 (2020) 3, S. 399-414 (2020)
|
|
BASE
|
|
Show details
|
|
13 |
PHOIBLE 2.0 phonemic inventories for Swedish
|
|
: Max Planck Institute for the Science of Human History, 2019
|
|
BASE
|
|
Show details
|
|
14 |
ELMo embeddings models for seven languages
|
|
Ulčar, Matej. - : Faculty of Computer and Information Science, University of Ljubljana, 2019
|
|
Abstract:
ELMo language model (https://github.com/allenai/bilm-tf) used to produce contextual word embeddings, trained on large monolingual corpora for 7 languages: Slovenian, Croatian, Finnish, Estonian, Latvian, Lithuanian and Swedish. Each language's model was trained for approximately 10 epochs. Corpora sizes used in training range from over 270 M tokens in Latvian to almost 2 B tokens in Croatian. About 1 million most common tokens were provided as vocabulary during the training for each language model. The model can also infer OOV words, since the neural network input is on the character level. Each model is in its own .tar.gz archive, consisting of two files: pytorch weights (.hdf5) and options (.json). Both are needed for model inference, using allennlp (https://github.com/allenai/allennlp/blob/master/tutorials/how_to/elmo.md) python library.
|
|
Keyword:
contextual embeddings; Croatian language; ELMo; Estonian language; Finnish language; Latvian language; Lithuanian language; Slovenian language; Swedish language; word embeddings
|
|
URL: http://hdl.handle.net/11356/1277
|
|
BASE
|
|
Hide details
|
|
18 |
Concreteness and imageability lexicon MEGA.HR-Crossling
|
|
Ljubešić, Nikola. - : Jožef Stefan Institute, 2018. : Faculty of Humanities and Social Sciences, University of Zagreb, 2018
|
|
BASE
|
|
Show details
|
|
|
|