Geodesic
Improving classification robustness for noisy texts with robust word vectors
Zapiski Nauchnykh Seminarov POMI, Investigations on applied mathematics and informatics. Part I, Tome 499 (2021), pp. 236-247

Voir la notice de l'article provenant de la source Math-Net.Ru

Text classification is a fundamental task in natural language processing, and a huge body of research has been devoted to it. However, there has been little work on investigating noi se robustness for the developed approaches. In this work, we are bridging this gap, introducing results on noise robustness testing of modern text classification architectures for Engl ish and Russian languages. We benchmark the CharCNN and SentenceCNN models and introduce a new model, called RoVe, that we show to be the most robust to noise. 
@article{ZNSL_2021_499_a12,
     author = {V. Malykh and V. Lyalin},
     title = {Improving classification robustness for noisy texts with robust word vectors},
     journal = {Zapiski Nauchnykh Seminarov POMI},
     pages = {236--247},
     publisher = {mathdoc},
     volume = {499},
     year = {2021},
     language = {en},
     url = {http://geodesic.mathdoc.fr/item/ZNSL_2021_499_a12/}
}
TY  - JOUR
AU  - V. Malykh
AU  - V. Lyalin
TI  - Improving classification robustness for noisy texts with robust word vectors
JO  - Zapiski Nauchnykh Seminarov POMI
PY  - 2021
SP  - 236
EP  - 247
VL  - 499
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/ZNSL_2021_499_a12/
LA  - en
ID  - ZNSL_2021_499_a12
ER  - 
%0 Journal Article
%A V. Malykh
%A V. Lyalin
%T Improving classification robustness for noisy texts with robust word vectors
%J Zapiski Nauchnykh Seminarov POMI
%D 2021
%P 236-247
%V 499
%I mathdoc
%U http://geodesic.mathdoc.fr/item/ZNSL_2021_499_a12/
%G en
%F ZNSL_2021_499_a12
V. Malykh; V. Lyalin. Improving classification robustness for noisy texts with robust word vectors. Zapiski Nauchnykh Seminarov POMI, Investigations on applied mathematics and informatics. Part I, Tome 499 (2021), pp. 236-247. http://geodesic.mathdoc.fr/item/ZNSL_2021_499_a12/