Communications in Computer and Information Science, pages 91-103

Application of a Hybrid Bi-LSTM-CRF model to the task of Russian Named Entity Recognition

Publication type: Book Chapter
Publication date: 2017-11-28
Quartile SCImago
Q4
Quartile WOS
—
Impact factor: —
ISSN: 18650929
Abstract
Named Entity Recognition (NER) is one of the most common tasks of the natural language processing. The purpose of NER is to find and classify tokens in text documents into predefined categories called tags, such as person names, quantity expressions, percentage expressions, names of locations, organizations, as well as expression of time, currency and others. Although there is a number of approaches have been proposed for this task in Russian language, it still has a substantial potential for the better solutions. In this work, we studied several deep neural network models starting from vanilla Bi-directional Long Short Term Memory (Bi-LSTM) then supplementing it with Conditional Random Fields (CRF) as well as highway networks and finally adding external word embeddings. All models were evaluated across three datasets Gareev’s, Person-1000 and FactRuEval 2016. We found that extension of Bi-LSTM model with CRF significantly increased the quality of predictions. Encoding input tokens with external word embeddings reduced training time and allowed to achieve state of the art for the Russian NER task.
By date By citations
By date By citations

Citations by journals

1
2
InterCarto InterGIS, 2, 20%
InterCarto InterGIS
2 publications, 20%
Lecture Notes in Electrical Engineering
Lecture Notes in Electrical Engineering, 2, 20%
Lecture Notes in Electrical Engineering
2 publications, 20%
Scientometrics
Scientometrics, 1, 10%
Scientometrics
1 publication, 10%
Arabian Journal for Science and Engineering
Arabian Journal for Science and Engineering, 1, 10%
Arabian Journal for Science and Engineering
1 publication, 10%
Lecture Notes in Computer Science
Lecture Notes in Computer Science, 1, 10%
Lecture Notes in Computer Science
1 publication, 10%
Modeling and Analysis of Information Systems
Modeling and Analysis of Information Systems, 1, 10%
Modeling and Analysis of Information Systems
1 publication, 10%
1
2

Citations by publishers

1
2
3
4
5
Springer Nature
Springer Nature, 5, 50%
Springer Nature
5 publications, 50%
LLC Kartfond, 2, 20%
LLC Kartfond
2 publications, 20%
P.G. Demidov Yaroslavl State University
P.G. Demidov Yaroslavl State University, 1, 10%
P.G. Demidov Yaroslavl State University
1 publication, 10%
1
2
3
4
5
  • We do not take into account publications that without a DOI.
  • Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
  • Statistics recalculated weekly.
Metrics
Share
Cite this
GOST |
Cite this
GOST Copy
Le T. A. et al. Application of a Hybrid Bi-LSTM-CRF model to the task of Russian Named Entity Recognition // Communications in Computer and Information Science. 2017. pp. 91-103.
GOST all authors (up to 50) Copy
Le T. A., Arkhipov M. Y., Burtsev M. S. Application of a Hybrid Bi-LSTM-CRF model to the task of Russian Named Entity Recognition // Communications in Computer and Information Science. 2017. pp. 91-103.
RIS |
Cite this
RIS Copy
TY - GENERIC
DO - 10.1007/978-3-319-71746-3_8
UR - https://doi.org/10.1007%2F978-3-319-71746-3_8
TI - Application of a Hybrid Bi-LSTM-CRF model to the task of Russian Named Entity Recognition
T2 - Communications in Computer and Information Science
AU - Le, The Anh
AU - Arkhipov, Mikhail Y
AU - Burtsev, Mikhail S.
PY - 2017
DA - 2017/11/28 00:00:00
PB - Springer Nature
SP - 91-103
SN - 1865-0929
ER -
BibTex
Cite this
BibTex Copy
@incollection{2017_Le,
author = {The Anh Le and Mikhail Y Arkhipov and Mikhail S. Burtsev},
title = {Application of a Hybrid Bi-LSTM-CRF model to the task of Russian Named Entity Recognition},
publisher = {Springer Nature},
year = {2017},
pages = {91--103},
month = {nov}
}
Found error?