DE eng

Search in the Catalogues and Directories

Hits 1 – 2 of 2

1
Towards a Multi-view Language Representation: A Shared Space of Discrete and Continuous Language Features ...
Abstract: Linguistic typology databases contain valuable knowledge of the distinguishing properties of different languages. Typically they contain sparse discrete features that are difficult to integrate into computational methods, and dense task-learned language vectors have emerged in response. To join both worlds, we compute a shared space between discrete (binary) and continuous features using canonical correlation analysis. We evaluate the new language representation against a concatenation baseline in typological feature prediction and in phylogenetic inference, obtaining promising results to explore further. ...
URL: https://zenodo.org/record/3923625
https://dx.doi.org/10.5281/zenodo.3923625
BASE
Hide details
2
Towards a Multi-view Language Representation: A Shared Space of Discrete and Continuous Language Features ...
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
2
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern