Fuzzy Ontology and LSTM-Based Text Mining: A Transportation Network Monitoring System for Assisting Travel

Ali, Farman; El–Sappagh, Shaker; Kwak, Daehan

doi:10.3390/s19020234

Cited by 71 publications

(43 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jiang et al [17] used LSTM networks for identifying personal health experiences from tweets. Similarly, previous work underlines the high utility of word embeddings and LSTM/BiLSTM networks for textual data mining and classification through social media posts and other sources [22][23][24]. Although these are framed in other problem domains, their results highlight the advantages of deep learning methodologies against conventional machine learning models for similar tasks.…”

Section: Related Workmentioning

confidence: 92%

Using BiLSTM Networks for Context-Aware Deep Sensitivity Labelling on Conversational Data

Pogiatzis

Samakovitis

2020

Applied Sciences

View full text Add to dashboard Cite

Information privacy is a critical design feature for any exchange system, with privacy-preserving applications requiring, most of the time, the identification and labelling of sensitive information. However, privacy and the concept of “sensitive information” are extremely elusive terms, as they are heavily dependent upon the context they are conveyed in. To accommodate such specificity, we first introduce a taxonomy of four context classes to categorise relationships of terms with their textual surroundings by meaning, interaction, precedence, and preference. We then propose a predictive context-aware model based on a Bidirectional Long Short Term Memory network with Conditional Random Fields (BiLSTM + CRF) to identify and label sensitive information in conversational data (multi-class sensitivity labelling). We train our model on a synthetic annotated dataset of real-world conversational data categorised in 13 sensitivity classes that we derive from the P3P standard. We parameterise and run a series of experiments featuring word and character embeddings and introduce a set of auxiliary features to improve model performance. Our results demonstrate that the BiLSTM + CRF model architecture with BERT embeddings and WordShape features is the most effective (F1 score 96.73%). Evaluation of the model is conducted under both temporal and semantic contexts, achieving a 76.33% F1 score on unseen data and outperforms Google’s Data Loss Prevention (DLP) system on sensitivity labelling tasks.

show abstract

Section: Related Workmentioning

confidence: 92%

Using BiLSTM Networks for Context-Aware Deep Sensitivity Labelling on Conversational Data

Pogiatzis

Samakovitis

2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…When faced with very little information, shallow structures can be used to achieve faster convergence and consume less computing resources. Ali et al [22] proposed a new type of semantic knowledge based on the Word2vec model, which used the bidirectional long short-term memory (Bi-LSTM) method to improve the traffic feature extraction and text classification tasks.…”

Section: Related Workmentioning

confidence: 99%

NEWLSTM: An Optimized Long Short-Term Memory Language Model for Sequence Prediction

et al. 2020

View full text Add to dashboard Cite

The long short-term memory (LSTM) model trained on the universal language modeling task overcomes the bottleneck of vanishing gradients in the traditional recurrent neural network (RNN) and shows excellent performance in processing multiple tasks generated by natural language processing. Although LSTM effectively alleviates the vanishing gradient problem in the RNN, the information will be greatly lost in the long distance transmission, and there are still some limitations in its practical use. In this paper, we propose a new model called NEWLSTM, which improves the LSTM model, and alleviates the defects of too many parameters in LSTM and the vanishing gradient. The NEWLSTM model directly correlates the cell state information with current information. The traditional LSTM's input gate and forget gate are integrated, some components are deleted, the problems of too many LSTM parameters and complicated calculations are solved, and the iteration time is effectively reduced. In this paper, a neural network model is used to identify the relationship between input information sequences to predict the language sequence. The experimental results show that the improved new model is simpler than traditional LSTM models and LSTM variants on multiple test sets. NEWLSTM has better overall stability and can better solve the sparse words problem. INDEX TERMS Gate fusion, exploding gradient, long short-term memory, recurrent neural network.

show abstract

“…However, ITSs may not be able to collect accurate traffic information from these sensors. In addition, in social media, information related to traffic comes with cross-domain text information, which makes the task of transport text mining and classification more difficult for ITSs [ 6 , 7 , 8 , 9 ]. This paper takes the relation extraction of cross-domain information as an entry point to explore cross-domain text mining and classification techniques.…”

Section: Introductionmentioning

confidence: 99%

Graph Adaptation Network with Domain-Specific Word Alignment for Cross-Domain Relation Extraction

Wang

Yan

et al. 2020

Sensors

View full text Add to dashboard Cite

Cross-domain relation extraction has become an essential approach when target domain lacking labeled data. Most existing works adapted relation extraction models from the source domain to target domain through aligning sequential features, but failed to transfer non-local and non-sequential features such as word co-occurrence which are also critical for cross-domain relation extraction. To address this issue, in this paper, we propose a novel tripartite graph architecture to adapt non-local features when there is no labeled data in the target domain. The graph uses domain words as nodes to model the co-occurrence relation between domain-specific words and domain-independent words. Through graph convolutions on the tripartite graph, the information of domain-specific words is propagated so that the word representation can be fine-tuned to align domain-specific features. In addition, unlike the traditional graph structure, the weights of edges innovatively combine fixed weight and dynamic weight, to capture the global non-local features and avoid introducing noise to word representation. Experiments on three domains of ACE2005 datasets show that our method outperforms the state-of-the-art models by a big margin.

show abstract

Fuzzy Ontology and LSTM-Based Text Mining: A Transportation Network Monitoring System for Assisting Travel

Cited by 71 publications

References 56 publications

Using BiLSTM Networks for Context-Aware Deep Sensitivity Labelling on Conversational Data

Using BiLSTM Networks for Context-Aware Deep Sensitivity Labelling on Conversational Data

NEWLSTM: An Optimized Long Short-Term Memory Language Model for Sequence Prediction

Graph Adaptation Network with Domain-Specific Word Alignment for Cross-Domain Relation Extraction

Contact Info

Product

Resources

About