TLR at BSNLP2019: A Multilingual Named Entity Recognition System

被引：0

作者：

Moreno, Jose G. ^{[1
]}

Pontes, Elvys Linhares ^{[2
,3
]}

Coustaty, Mickael ^{[2
]}

Doucet, Antoine ^{[2
]}

机构：

[1] Univ Toulouse, IRIT, UMR 5505, CNRS, Toulouse, France

[2] Univ La Rochelle, Lab L3i, La Rochelle, France

[3] Univ Avignon, Avignon, France

来源：

7TH WORKSHOP ON BALTO-SLAVIC NATURAL LANGUAGE PROCESSING (BSNLP'2019) | 2019年

基金：

欧盟地平线“2020”;

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents our participation at the shared task on multilingual named entity recognition at BSNLP2019. Our strategy is based on a standard neural architecture for sequence labeling. In particular, we use a mixed model which combines multilingual-contextual and language-specific embeddings. Our only submitted run is based on a voting schema using multiple models, one for each of the four languages of the task (Bulgarian, Czech, Polish, and Russian) and another for English. Results for named entity recognition are encouraging for all languages, varying from 60% to 83% in terms of Strict and Relaxed metrics, respectively.

引用

页码：83 / 88

页数：6

共 21 条

[1]

[Anonymous], 2019, P 7 WORKSH BALT SLAV

[2]

Bojanowski Piotr, 2017, Trans. Assoc. Comput. Linguist., V5, P135, DOI DOI 10.1162/TACL_A_00051

[3]

Chiticariu L., 2010, 2010 C EMP METH NAT, P1002

[4]

Devlin Jacob, 2019, 2019 ANN C N AM ASS

[5]

Florian R., 2003, Proceedings of CoNLL-2003, P168, DOI DOI 10.3115/1119176.1119201

[6]

Grave E., 2018, P INT C LANGUAGE RES

[7]

Ji Heng., 2014, Proc. Text Analysis Conference (TAC2014), P1333

[8]

Ji Heng, 2017, P TEXT AN C TAC2017

[9]

Ji Heng, 2015, P TEXT AN C TAC2015

[10]

Ji Heng, 2016, P TEXT AN C TAC2016

← 1 2 3 →