Deep Learning-Based Named Entity Recognition and Knowledge Graph Construction for Geological Hazards
70
TL;DR: A deep learning-based NER model, which combines a multi-branch bidirectional gated recurrent unit (BiGRU) layer and a conditional random field (CRF) model, is proposed, which outperformed state-of-the-art models.
read more
Abstract: Constructing a knowledge graph of geological hazards literature can facilitate the reuse of geological hazards literature and provide a reference for geological hazard governance. Named entity recognition (NER), as a core technology for constructing a geological hazard knowledge graph, has to face the challenges that named entities in geological hazard literature are diverse in form, ambiguous in semantics, and uncertain in context. This can introduce difficulties in designing practical features during the NER classification. To address the above problem, this paper proposes a deep learning-based NER model; namely, the deep, multi-branch BiGRU-CRF model, which combines a multi-branch bidirectional gated recurrent unit (BiGRU) layer and a conditional random field (CRF) model. In an end-to-end and supervised process, the proposed model automatically learns and transforms features by a multi-branch bidirectional GRU layer and enhances the output with a CRF layer. Besides the deep, multi-branch BiGRU-CRF model, we also proposed a pattern-based corpus construction method to construct the corpus needed for the deep, multi-branch BiGRU-CRF model. Experimental results indicated the proposed deep, multi-branch BiGRU-CRF model outperformed state-of-the-art models. The proposed deep, multi-branch BiGRU-CRF model constructed a large-scale geological hazard literature knowledge graph containing 34,457 entities nodes and 84,561 relations.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Domain-specific knowledge graphs: A survey
TL;DR: This survey is the first to provide an inclusive definition to the notion of domain KG, and a comprehensive review of the state-of-the-art approaches drawn from academic works relevant to seven dissimilar domains of knowledge is provided.
308
Knowledge graph construction and application in geosciences: A review
TL;DR: In this paper , a comprehensive review of knowledge graph (KG) construction and implementation in geosciences is presented, which consists of four major parts: 1) concepts relevant to KG and approaches for KG construction, 2) KG application in data collection, curation, and service, 3] KG analysis in data analysis and 4) challenges and trends of geoscience KG creation and application in the near future.
78
A knowledge graph method for hazardous chemical management: Ontology design and entity identification
TL;DR: A deep neural model, BERT-CRF, is adopted, based on bidirectional encoder representation from transformers (BERT) model and conditional random field (CRF) model, and it achieves good results, exhibiting the effectiveness in the task of named entity recognition in the chemical industry.
69
Chinese mineral named entity recognition based on BERT model
TL;DR: Zhang et al. as discussed by the authors used bidirectional encoder representations from Transformers (BERT) to create word embeddings for Chinese mineral text and combined the transfer matrix of the CRF algorithm to improve the accuracy of sequence labeling.
52
Topic analysis and development in knowledge graph research: A bibliometric review on three decades
TL;DR: Several widely studied issues such as knowledge graph embedding, search and query based on knowledge graphs, and knowledge graphs for intangible cultural heritage are highlighted.
48
References
•Posted Content
Speech Recognition with Deep Recurrent Neural Networks
TL;DR: In this paper, deep recurrent neural networks (RNNs) are used to combine the multiple levels of representation that have proved so effective in deep networks with the flexible use of long range context that empowers RNNs.
5.3K
Learning to Forget: Continual Prediction with LSTM
TL;DR: This work identifies a weakness of LSTM networks processing continual input streams that are not a priori segmented into subsequences with explicitly marked ends at which the network's internal state could be reset, and proposes a novel, adaptive forget gate that enables an LSTm cell to learn to reset itself at appropriate times, thus releasing internal resources.
5.1K
•Proceedings Article
TextRank: Bringing Order into Text
Rada Mihalcea,Paul Tarau +1 more
- 01 Jul 2004
TL;DR: TextRank, a graph-based ranking model for text processing, is introduced and it is shown how this model can be successfully used in natural language applications.
•Posted Content
On the difficulty of training Recurrent Neural Networks
TL;DR: This paper proposes a gradient norm clipping strategy to deal with exploding gradients and a soft constraint for the vanishing gradients problem and validates empirically the hypothesis and proposed solutions.
4.3K
Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling
Hasim Sak,Andrew W. Senior,Francoise Beaufays +2 more
- 01 Jan 2014
TL;DR: The first distributed training of LSTM RNNs using asynchronous stochastic gradient descent optimization on a large cluster of machines is introduced and it is shown that a two-layer deep LSTm RNN where each L STM layer has a linear recurrent projection layer can exceed state-of-the-art speech recognition performance.