21 |
Improving the Performance of Vietnamese&ndash ; Korean Neural Machine Translation with Contextual Embedding
|
|
|
|
In: Applied Sciences ; Volume 11 ; Issue 23 (2021)
|
|
BASE
|
|
Show details
|
|
22 |
Collecting and annotating corpora for three under-resourced languages of France: Methodological issues
|
|
|
|
BASE
|
|
Show details
|
|
24 |
Collecting and annotating corpora for three under-resourced languages of France: Methodological issues
|
|
|
|
BASE
|
|
Show details
|
|
25 |
The impact of Arabic part of speech tagging on sentiment analysis: A new corpus and deep learning approach
|
|
|
|
In: Test Series for Scopus Harvesting 2021 (2021)
|
|
BASE
|
|
Show details
|
|
26 |
Testing for Grammatical Category Abstraction in Neural Language Models
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2021)
|
|
BASE
|
|
Show details
|
|
28 |
Crowdsourcing linguistic resources for natural non-standardised languages processing ; Myriadisation de ressources linguistiques pour le traitement automatique de langues non standardisées
|
|
|
|
In: https://hal.archives-ouvertes.fr/tel-03083213 ; Informatique et langage [cs.CL]. Sorbonne Universite, 2020. Français (2020)
|
|
BASE
|
|
Show details
|
|
29 |
Hierarchical-Task Reservoir for Anytime POS Tagging from Continuous Speech
|
|
|
|
In: 2020 International Joint Conference on Neural Networks (IJCNN 2020) ; https://hal.inria.fr/hal-02594495 ; 2020 International Joint Conference on Neural Networks (IJCNN 2020), Jul 2020, Glasgow, Scotland, United Kingdom ; https://wcci2020.org/ (2020)
|
|
BASE
|
|
Show details
|
|
31 |
The CLASSLA-StanfordNLP model for morphosyntactic annotation of standard Macedonian 1.0
|
|
|
|
BASE
|
|
Show details
|
|
32 |
The CLASSLA-StanfordNLP model for morphosyntactic annotation of standard Serbian 1.1
|
|
|
|
BASE
|
|
Show details
|
|
34 |
The CLASSLA-StanfordNLP model for morphosyntactic annotation of standard Croatian 1.1
|
|
|
|
BASE
|
|
Show details
|
|
35 |
Annotated Corpus of Pre-Standardized Balkan Slavic Literature
|
|
Šimko, Ivan. - : Slavic Seminary, University of Zurich, 2020
|
|
BASE
|
|
Show details
|
|
36 |
The CLASSLA-StanfordNLP model for morphosyntactic annotation of standard Bulgarian 1.0
|
|
|
|
BASE
|
|
Show details
|
|
37 |
The CLASSLA-StanfordNLP model for morphosyntactic annotation of non-standard Serbian 1.0
|
|
|
|
BASE
|
|
Show details
|
|
38 |
The CLASSLA-StanfordNLP model for morphosyntactic annotation of non-standard Croatian 1.0
|
|
|
|
BASE
|
|
Show details
|
|
39 |
The CLASSLA-StanfordNLP model for morphosyntactic annotation of non-standard Slovenian 1.0
|
|
|
|
BASE
|
|
Show details
|
|
40 |
The CLASSLA-StanfordNLP model for morphosyntactic annotation of standard Slovenian 1.1
|
|
|
|
Abstract:
This model for morphosyntactic annotation of standard Slovenian was built with the CLASSLA-StanfordNLP tool (https://github.com/clarinsi/classla-stanfordnlp) by training on the ssj500k training corpus (http://hdl.handle.net/11356/1210) and using the CLARIN.SI-embed.sl word embeddings (http://hdl.handle.net/11356/1204). The model produces simultaneously UPOS, FEATS and XPOS (MULTEXT-East) labels. The estimated F1 of the XPOS annotations is ~97.06. The difference to the previous version of the model is that now the whole XPOS tag is predicted and not specific characters, as was the case in stanfordnlp, which resulted in illegal XPOS tags (and slightly decreased performance).
|
|
Keyword:
language model; part-of-speech tagging
|
|
URL: http://hdl.handle.net/11356/1312
|
|
BASE
|
|
Hide details
|
|
|
|