DE eng

Search in the Catalogues and Directories

Hits 1 – 12 of 12

1
Universal Segmentations 1.0 (UniSegments 1.0)
Žabokrtský, Zdeněk; Bafna, Nyati; Bodnár, Jan. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2022
BASE
Show details
2
DeriNet 2.1
Vidra, Jonáš; Žabokrtský, Zdeněk; Kyjánek, Lukáš. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2021
BASE
Show details
3
Universal Derivations v1.1
Kyjánek, Lukáš; Žabokrtský, Zdeněk; Vidra, Jonáš. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2021
BASE
Show details
4
Universal Derivations v1.0
Kyjánek, Lukáš; Žabokrtský, Zdeněk; Vidra, Jonáš. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2020
BASE
Show details
5
DeriNet 2.0
Vidra, Jonáš; Žabokrtský, Zdeněk; Kyjánek, Lukáš. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2019
BASE
Show details
6
Universal Derivations v0.5
Kyjánek, Lukáš; Žabokrtský, Zdeněk; Vidra, Jonáš. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2019
BASE
Show details
7
Derivational Morphological Relations in Word Embeddings ...
BASE
Show details
8
DeriNet 1.6 (2018-09-24)
Vidra, Jonáš; Kyjánek, Lukáš; Ševčíková, Magda. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2018
BASE
Show details
9
Morphological and Language-Agnostic Word Segmentation for NMT ...
Abstract: The state of the art of handling rich morphology in neural machine translation (NMT) is to break word forms into subword units, so that the overall vocabulary size of these units fits the practical limits given by the NMT model and GPU memory capacity. In this paper, we compare two common but linguistically uninformed methods of subword construction (BPE and STE, the method implemented in Tensor2Tensor toolkit) and two linguistically-motivated methods: Morfessor and one novel method, based on a derivational dictionary. Our experiments with German-to-Czech translation, both morphologically rich, document that so far, the non-motivated methods perform better. Furthermore, we iden- tify a critical difference between BPE and STE and show a simple pre- processing step for BPE that considerably increases translation quality as evaluated by automatic measures. ... : In print. To appear in TSD 2018 ...
Keyword: Computation and Language cs.CL; FOS Computer and information sciences
URL: https://dx.doi.org/10.48550/arxiv.1806.05482
https://arxiv.org/abs/1806.05482
BASE
Hide details
10
DeriNet 1.5
Vidra, Jonáš; Žabokrtský, Zdeněk; Ševčíková, Magda. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2017
BASE
Show details
11
DeriNet 1.2
Vidra, Jonáš; Žabokrtský, Zdeněk; Ševčíková, Magda. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2016
BASE
Show details
12
DeriNet 1.0
Vidra, Jonáš; Žabokrtský, Zdeněk; Ševčíková, Magda. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2015
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
12
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern