The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Les systèmes de reconnaissance d'entités nommées (NER) sont souvent réalisés par des méthodes supervisées telles que les méthodes CRF et les réseaux neuronaux, qui nécessitent de grandes données annotées. Dans certains domaines pour lesquels de petites données de formation annotées sont disponibles, des méthodes d'apprentissage multi-domaines ou multi-tâches sont souvent utilisées. Dans cet article, nous explorons les méthodes qui utilisent le domaine d'actualités et la tâche de segmentation de mots chinois (CWS) pour améliorer les performances de reconnaissance des entités nommées chinoises dans le domaine Weibo. Nous proposons dans un premier temps deux modèles de base combinant des informations multi-domaines et multi-tâches. Les deux modèles de base partagent des informations entre différents domaines et tâches en partageant simplement des paramètres. Ensuite, nous proposons un modèle Double ADVersarial (modèle DoubADV). Le modèle utilise deux réseaux contradictoires prenant en compte les fonctionnalités partagées et privées dans différents domaines et tâches. Les résultats expérimentaux montrent que notre modèle DoubADV surpasse les autres modèles de base et atteint des performances de pointe par rapport aux travaux précédents dans des situations multi-domaines et multi-tâches.
Yun HU
University of Chinese Academy of Science
Changwen ZHENG
Institute of Software Chinese Academy of Sciences
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Yun HU, Changwen ZHENG, "A Double Adversarial Network Model for Multi-Domain and Multi-Task Chinese Named Entity Recognition" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 7, pp. 1744-1752, July 2020, doi: 10.1587/transinf.2019EDP7253.
Abstract: Named Entity Recognition (NER) systems are often realized by supervised methods such as CRF and neural network methods, which require large annotated data. In some domains that small annotated training data is available, multi-domain or multi-task learning methods are often used. In this paper, we explore the methods that use news domain and Chinese Word Segmentation (CWS) task to improve the performance of Chinese named entity recognition in weibo domain. We first propose two baseline models combining multi-domain and multi-task information. The two baseline models share information between different domains and tasks through sharing parameters simply. Then, we propose a Double ADVersarial model (DoubADV model). The model uses two adversarial networks considering the shared and private features in different domains and tasks. Experimental results show that our DoubADV model outperforms other baseline models and achieves state-of-the-art performance compared with previous works in multi-domain and multi-task situation.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDP7253/_p
Copier
@ARTICLE{e103-d_7_1744,
author={Yun HU, Changwen ZHENG, },
journal={IEICE TRANSACTIONS on Information},
title={A Double Adversarial Network Model for Multi-Domain and Multi-Task Chinese Named Entity Recognition},
year={2020},
volume={E103-D},
number={7},
pages={1744-1752},
abstract={Named Entity Recognition (NER) systems are often realized by supervised methods such as CRF and neural network methods, which require large annotated data. In some domains that small annotated training data is available, multi-domain or multi-task learning methods are often used. In this paper, we explore the methods that use news domain and Chinese Word Segmentation (CWS) task to improve the performance of Chinese named entity recognition in weibo domain. We first propose two baseline models combining multi-domain and multi-task information. The two baseline models share information between different domains and tasks through sharing parameters simply. Then, we propose a Double ADVersarial model (DoubADV model). The model uses two adversarial networks considering the shared and private features in different domains and tasks. Experimental results show that our DoubADV model outperforms other baseline models and achieves state-of-the-art performance compared with previous works in multi-domain and multi-task situation.},
keywords={},
doi={10.1587/transinf.2019EDP7253},
ISSN={1745-1361},
month={July},}
Copier
TY - JOUR
TI - A Double Adversarial Network Model for Multi-Domain and Multi-Task Chinese Named Entity Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 1744
EP - 1752
AU - Yun HU
AU - Changwen ZHENG
PY - 2020
DO - 10.1587/transinf.2019EDP7253
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2020
AB - Named Entity Recognition (NER) systems are often realized by supervised methods such as CRF and neural network methods, which require large annotated data. In some domains that small annotated training data is available, multi-domain or multi-task learning methods are often used. In this paper, we explore the methods that use news domain and Chinese Word Segmentation (CWS) task to improve the performance of Chinese named entity recognition in weibo domain. We first propose two baseline models combining multi-domain and multi-task information. The two baseline models share information between different domains and tasks through sharing parameters simply. Then, we propose a Double ADVersarial model (DoubADV model). The model uses two adversarial networks considering the shared and private features in different domains and tasks. Experimental results show that our DoubADV model outperforms other baseline models and achieves state-of-the-art performance compared with previous works in multi-domain and multi-task situation.
ER -