GNER: A Generative Model for Geological Named Entity Recognition Without Labeled Data Using Deep Learning

Abstract A variety of detailed data about geological topics and geoscience knowledge are buried in the geoscience literature and rarely used. Named entity recognition (NER) provides both opportunities and challenges to leverage this wealth of data in the geoscience literature for data analysis and f...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Qinjun Qiu, Zhong Xie, Liang Wu, Liufeng Tao
Formato:	article
Lenguaje:	EN
Publicado:	American Geophysical Union (AGU) 2019
Materias:	natural language processing named entity recognition geoscience domain unsupervised learning Astronomy QB1-991 Geology QE1-996.5
Acceso en línea:	https://doaj.org/article/8b19d8b977604258a40f352ff20ac254
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8b19d8b977604258a40f352ff20ac254
record_format	dspace
spelling	oai:doaj.org-article:8b19d8b977604258a40f352ff20ac2542021-11-30T22:55:32ZGNER: A Generative Model for Geological Named Entity Recognition Without Labeled Data Using Deep Learning2333-508410.1029/2019EA000610https://doaj.org/article/8b19d8b977604258a40f352ff20ac2542019-06-01T00:00:00Zhttps://doi.org/10.1029/2019EA000610https://doaj.org/toc/2333-5084Abstract A variety of detailed data about geological topics and geoscience knowledge are buried in the geoscience literature and rarely used. Named entity recognition (NER) provides both opportunities and challenges to leverage this wealth of data in the geoscience literature for data analysis and further information extraction. Existing NER models and techniques are mainly based on rule‐based and supervised approaches, and developing such systems requires a costly manual effort. In this paper, we first design a generic stepwise framework for domain‐specific NER. Following this framework, domain‐specific entities and domain‐general words are collected and selected as seed terms. Normalization and grouping processes are then applied to these seed terms for further analysis. A random extraction algorithm based on a unigram language model is used to generate a large‐scale training data set consisting of probabilistically labeled pseudosentences. Each generated sentence is then used as input to the self‐training and learning algorithm. Experimental results on two constructed data sets demonstrate that the proposed model effectively recognizes and identifies geological named entities.Qinjun QiuZhong XieLiang WuLiufeng TaoAmerican Geophysical Union (AGU)articlenatural language processingnamed entity recognitiongeoscience domainunsupervised learningAstronomyQB1-991GeologyQE1-996.5ENEarth and Space Science, Vol 6, Iss 6, Pp 931-946 (2019)
institution	DOAJ
collection	DOAJ
language	EN
topic	natural language processing named entity recognition geoscience domain unsupervised learning Astronomy QB1-991 Geology QE1-996.5
spellingShingle	natural language processing named entity recognition geoscience domain unsupervised learning Astronomy QB1-991 Geology QE1-996.5 Qinjun Qiu Zhong Xie Liang Wu Liufeng Tao GNER: A Generative Model for Geological Named Entity Recognition Without Labeled Data Using Deep Learning
description	Abstract A variety of detailed data about geological topics and geoscience knowledge are buried in the geoscience literature and rarely used. Named entity recognition (NER) provides both opportunities and challenges to leverage this wealth of data in the geoscience literature for data analysis and further information extraction. Existing NER models and techniques are mainly based on rule‐based and supervised approaches, and developing such systems requires a costly manual effort. In this paper, we first design a generic stepwise framework for domain‐specific NER. Following this framework, domain‐specific entities and domain‐general words are collected and selected as seed terms. Normalization and grouping processes are then applied to these seed terms for further analysis. A random extraction algorithm based on a unigram language model is used to generate a large‐scale training data set consisting of probabilistically labeled pseudosentences. Each generated sentence is then used as input to the self‐training and learning algorithm. Experimental results on two constructed data sets demonstrate that the proposed model effectively recognizes and identifies geological named entities.
format	article
author	Qinjun Qiu Zhong Xie Liang Wu Liufeng Tao
author_facet	Qinjun Qiu Zhong Xie Liang Wu Liufeng Tao
author_sort	Qinjun Qiu
title	GNER: A Generative Model for Geological Named Entity Recognition Without Labeled Data Using Deep Learning
title_short	GNER: A Generative Model for Geological Named Entity Recognition Without Labeled Data Using Deep Learning
title_full	GNER: A Generative Model for Geological Named Entity Recognition Without Labeled Data Using Deep Learning
title_fullStr	GNER: A Generative Model for Geological Named Entity Recognition Without Labeled Data Using Deep Learning
title_full_unstemmed	GNER: A Generative Model for Geological Named Entity Recognition Without Labeled Data Using Deep Learning
title_sort	gner: a generative model for geological named entity recognition without labeled data using deep learning
publisher	American Geophysical Union (AGU)
publishDate	2019
url	https://doaj.org/article/8b19d8b977604258a40f352ff20ac254
work_keys_str_mv	AT qinjunqiu gneragenerativemodelforgeologicalnamedentityrecognitionwithoutlabeleddatausingdeeplearning AT zhongxie gneragenerativemodelforgeologicalnamedentityrecognitionwithoutlabeleddatausingdeeplearning AT liangwu gneragenerativemodelforgeologicalnamedentityrecognitionwithoutlabeleddatausingdeeplearning AT liufengtao gneragenerativemodelforgeologicalnamedentityrecognitionwithoutlabeleddatausingdeeplearning
_version_	1718406214418694144

GNER: A Generative Model for Geological Named Entity Recognition Without Labeled Data Using Deep Learning

Ejemplares similares