DE eng

Search in the Catalogues and Directories

Hits 1 – 12 of 12

1
Enhancing Sequence-to-Sequence Neural Lemmatization with External Resources ...
BASE
Show details
2
Evaluating Multilingual BERT for Estonian ...
BASE
Show details
3
EstBERT: A Pretrained Language-Specific BERT for Estonian ...
BASE
Show details
4
STransE: a novel embedding model of entities and relationships in knowledge bases ...
BASE
Show details
5
STransE : a novel embedding model of entities and relationships in knowledge bases
Nguyen, Dat Quoc; Sirts, Kairit; Qu, Lizhen. - : Red Hook, New York : Association for Computational Linguistics, 2016
BASE
Show details
6
Query-based single document summarization using an Ensemble Noisy Auto-Encoder
Yousefi Azar, Mahmood; Sirts, Kairit; Molla Aliod, Diego. - : Melbourne, Australia : Association for Computational Linguistics, 2015
BASE
Show details
7
POS induction with distributional and morphological information using a distance-dependent Chinese Restaurant Process
Sirts, Kairit; Eisenstein, Jacob; Elsner, Micha. - : Stroudsburg, PA : Association for Computational Linguistics, 2014
BASE
Show details
8
Minimally-supervised morphological segmentation using adaptor grammars
Sirts, Kairit; Goldwater, Sharon. - : Association for Computational Linguistics, 2013
BASE
Show details
9
Noisy-channel spelling correction models for Estonian learner language corpus lemmatisation
Sirts, Kairit. - : Amsterdam : IOS Press, 2012
BASE
Show details
10
A Hierarchical dirichlet process model for joint part-of-speech and morphology induction
Alumäe, Tanel; Sirts, Kairit. - : Stroudsburg, PA : Association for Computational Linguistics, 2012
Abstract: In this paper we present a fully unsupervised nonparametric Bayesian model that jointly induces POS tags and morphological segmentations. The model is essentially an infinite HMM that infers the number of states from data. Incorporating segmentation into the same model provides the morphological features to the system and eliminates the need to find them during preprocessing step. We show that learning both tasks jointly actually leads to better results than learning either task with gold standard data from the other task provided. The evaluation on multilingual data shows that the model produces state-of-the-art results on POS induction. ; 10 page(s)
URL: http://hdl.handle.net/1959.14/1148085
BASE
Hide details
11
Korpuste tükeldamine : rakendusi silpide ning allkeeltega ; Cutting the text corpora : applications with syllables and sub-languages
Sirts, Kairit; Võhandu, Leo. - : Eesti Rakenduslingvistika Uhing = Estonian Association for Applied Linguistics, 2009
BASE
Show details
12
Eesti silbisüsteemi struktuurist ; A preliminary structural view of the Estonian syllable system
Võhandu, Leo; Sirts, Kairit; Aab, Eik. - : Eesti Rakenduslingvistika Uhing, 2008
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