CNN for Modeling Sanskrit Originated Bengali and Hindi Language
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F22%3AN4K5R3E8" target="_blank" >RIV/00216208:11320/22:N4K5R3E8 - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2022.aacl-main.4" target="_blank" >https://aclanthology.org/2022.aacl-main.4</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
CNN for Modeling Sanskrit Originated Bengali and Hindi Language
Original language description
Though recent works have focused on modeling high resource languages, the area is still unexplored for low resource languages like Bengali and Hindi. We propose an end to end trainable memory efficient CNN architecture named CoCNN to handle specific characteristics such as high inflection, morphological richness, flexible word order and phonetical spelling errors of Bengali and Hindi. In particular, we introduce two learnable convolutional sub-models at word and at sentence level that are end to end trainable. We show that state-of-the-art (SOTA) Transformer models including pretrained BERT do not necessarily yield the best performance for Bengali and Hindi. CoCNN outperforms pretrained BERT with 16X less parameters and achieves much better performance than SOTA LSTMs on multiple real-world datasets. This is the first study on the effectiveness of different architectures from Convolution, Recurrent, and Transformer neural net paradigm for modeling Bengali and Hindi.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2022
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
ISBN
978-1-955917-65-0
ISSN
—
e-ISSN
—
Number of pages
10
Pages from-to
47-56
Publisher name
Association for Computational Linguistics
Place of publication
—
Event location
Online only
Event date
Jan 1, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—