A reproduction of Apple's bi-directional LSTM models for language identification in short strings

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10440893" target="_blank" >RIV/00216208:11320/21:10440893 - isvavai.cz</a>

Result on the web

<a href="https://aclanthology.org/2021.eacl-srw.6" target="_blank" >https://aclanthology.org/2021.eacl-srw.6</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.18653/v1/2021.eacl-srw.6" target="_blank" >10.18653/v1/2021.eacl-srw.6</a>

Result language

angličtina

Original language name

A reproduction of Apple's bi-directional LSTM models for language identification in short strings

Original language description

Language Identification is the task of identifying a document&apos;s language. For applications like automatic spell checker selection, language identification must use very short strings such as text message fragments. In this work, we reproduce a language identification architecture that Apple briefly sketched in a blog post. We confirm the bi-LSTM model&apos;s performance and find that it outperforms current open-source language identifiers. We further find that its language identification mistakes are due to confusion between related languages.

Czech name

—

Czech description

—

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)

Project

—

Continuities

—

Publication year

2021

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Student Research Workshop

ISBN

978-1-954085-04-6

ISSN

—

e-ISSN

—

Number of pages

7

Pages from-to

36-42

Publisher name

Association for Computational Linguistics

Place of publication

Stroudsburg

Event location

online

Event date

Apr 19, 2021

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—