1. |
- Tran, Son N., et al.
(författare)
-
Improving Recurrent Neural Networks with Predictive Propagation for Sequence Labelling
- 2018
-
Ingår i: Neural Information Processing. - Cham : Springer. - 9783030041663 - 9783030041670 ; , s. 452-462
-
Konferensbidrag (refereegranskat)abstract
- Recurrent neural networks (RNNs) is a useful tool for sequence labelling tasks in natural language processing. Although in practice RNNs suffer a problem of vanishing/exploding gradient, their compactness still offers efficiency and make them less prone to overfitting. In this paper we show that by propagating the prediction of previous labels we can improve the performance of RNNs while keeping the number of parameters in RNNs unchanged and adding only one more step for inference. As a result, the models are still more compact and efficient than other models with complex memory gates. In the experiment, we evaluate the idea on optical character recognition and Chunking which achieve promising results.
|
|
2. |
- Tran, Son N., et al.
(författare)
-
On multi-resident activity recognition in ambient smart-homes
- 2020
-
Ingår i: Artificial Intelligence Review. - : Springer. - 0269-2821 .- 1573-7462. ; 53:6, s. 3929-3945
-
Tidskriftsartikel (refereegranskat)abstract
- Increasing attention to the research on activity monitoring in smart homes has motivated the employment of ambient intelligence to reduce the deployment cost and solve the privacy issue. Several approaches have been proposed for multi-resident activity recognition, however, there still lacks a comprehensive benchmark for future research and practical selection of models. In this paper, we study different methods for multi-resident activity recognition and evaluate them on the same sets of data. In particular, we explore the effectiveness and efficiency of temporal learning algorithms using sequential data and non-temporal learning algorithms using temporally-manipulated features. In the experiments we compare and analyse the results of the studied methods using datasets from three smart homes.
|
|
3. |
- Vu, Xuan-Son, 1988-, et al.
(författare)
-
ETNLP : A Visual-Aided Systematic Approach to Select Pre-Trained Embeddings for a Down Stream Task
- 2019
-
Ingår i: Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019). - : Incoma Ltd.. - 9789544520557 - 9789544520564 ; , s. 1285-1294
-
Konferensbidrag (refereegranskat)abstract
- Given many recent advanced embedding models, selecting pre-trained wordembedding (a.k.a., word representation) models best fit for a specific downstream task is non-trivial. In this paper, we propose a systematic approach, called ETNLP, for extracting, evaluating, and visualizing multiple sets of pretrained word embeddings to determine which embeddings should be used in a downstream task. We demonstrate the effectiveness of the proposed approach on our pre-trained word embedding models in Vietnamese to select which models are suitable for a named entity recognition (NER) task. Specifically, we create a large Vietnamese word analogy list to evaluate and select the pre-trained embedding models for the task. We then utilize the selected embeddings for the NER task and achieve the new state-of-the-art results on the task benchmark dataset. We also apply the approach to another downstream task of privacy-guaranteed embedding selection, and show that it helps users quickly select the most suitable embeddings. In addition, we create an open-source system using the proposed systematic approach to facilitate similar studies on other NLP tasks. The source code and data are available at https://github.com/vietnlp/etnlp.
|
|
4. |
- Tran, Khanh-Tung, et al.
(författare)
-
MGLEP : multimodal graph learning for modeling emerging pandemics with big data
- 2024
-
Ingår i: Scientific Reports. - : Springer Nature. - 2045-2322. ; 14:1
-
Tidskriftsartikel (refereegranskat)abstract
- Accurate forecasting and analysis of emerging pandemics play a crucial role in effective public health management and decision-making. Traditional approaches primarily rely on epidemiological data, overlooking other valuable sources of information that could act as sensors or indicators of pandemic patterns. In this paper, we propose a novel framework, MGLEP, that integrates temporal graph neural networks and multi-modal data for learning and forecasting. We incorporate big data sources, including social media content, by utilizing specific pre-trained language models and discovering the underlying graph structure among users. This integration provides rich indicators of pandemic dynamics through learning with temporal graph neural networks. Extensive experiments demonstrate the effectiveness of our framework in pandemic forecasting and analysis, outperforming baseline methods across different areas, pandemic situations, and prediction horizons. The fusion of temporal graph learning and multi-modal data enables a comprehensive understanding of the pandemic landscape with less time lag, cheap cost, and more potential information indicators.
|
|
5. |
- Vu, Xuan-Son, 1988-, et al.
(författare)
-
dpUGC : learn differentially private representation for user generated contents
- 2023
-
Ingår i: Computational linguistics and intelligent text processing. - Cham : Springer. - 9783031243363 - 9783031243370 ; , s. 316-331
-
Konferensbidrag (refereegranskat)abstract
- This paper firstly proposes a simple yet efficient generalized approach to apply differential privacy to text representation (i.e., word embedding). Based on it, we propose a user-level approach to learn personalized differentially private word embedding model on user generated contents (UGC). To our best knowledge, this is the first work of learning user-level differentially private word embedding model from text for sharing. The proposed approaches protect the privacy of the individual from re-identification, especially provide better trade-off of privacy and data utility on UGC data for sharing. The experimental results show that the trained embedding models are applicable for the classic text analysis tasks (e.g., regression). Moreover, the proposed approaches of learning differentially private embedding models are both framework- and dataindependent, which facilitates the deployment and sharing. The source code is available at https://github.com/sonvx/dpText.
|
|
6. |
- Vu, Xuan-Son, 1988-, et al.
(författare)
-
MC-OCR Challenge : Mobile-Captured Image Document Recognition for Vietnamese Receipts
- 2021
-
Ingår i: Proceedings - 2021 RIVF International Conference on Computing and Communication Technologies, RIVF 2021. - : IEEE. - 9781665404358 ; , s. 88-93
-
Konferensbidrag (refereegranskat)abstract
- The paper describes the organisation of the "Mobile Captured Receipt Recognition Challenge"(MC-OCR) task at the RIVF conference 2021 1 on recognizing the fine-grained information in Vietnamese receipts captured using mobile devices. The task is organized as a multi-tasking model on a dataset containing 2, 436 Vietnamese receipts. The participants were challenged to build a model that is capable of (1) predicting receipt's quality based on readable information, and (2) recognizing textual information of four required information (i.e., "SELLER", "SELLER ADDRESS", "TIMESTAMP", and "TOTAL COST") in the receipts. MC-OCR challenge happened in one month and top winners of each task will present their solutions at RIVF 2021. Participants were competing on CodaLab.Org from 05th December 2020 to 23rd January 2021. All participants with valid submitted results were encouraged to submit their papers. Within one month, the challenge has attracted 105 participants and recorded about 1, 285 submission entries.
|
|
7. |
|
|
8. |
- Vu, Xuan-Son, 1988-, et al.
(författare)
-
Multimodal Review Generation with Privacy and Fairness Awareness
- 2020
-
Ingår i: Proceedings of the 28th International Conference on Computational Linguistics (COLING), 2020. - Stroudsburg, PA, USA : International Committee on Computational LinguisticsInternational Committee on Computational Linguistics. ; , s. 414-425
-
Konferensbidrag (refereegranskat)abstract
- Users express their opinions towards entities (e.g., restaurants) via online reviews which can be in diverse forms such as text, ratings, and images. Modeling reviews are advantageous for user behavior understanding which, in turn, supports various user-oriented tasks such as recommendation, sentiment analysis, and review generation. In this paper, we propose MG-PriFair, a multimodal neural-based framework, which generates personalized reviews with privacy and fairness awareness. Motivated by the fact that reviews might contain personal information and sentiment bias, we propose a novel differentially private (dp)-embedding model for training privacy guaranteed embeddings and an evaluation approach for sentiment fairness in the food-review domain. Experiments on our novel review dataset show that MG-PriFair is capable of generating plausibly long reviews while controlling the amount of exploited user data and using the least sentiment biased word embeddings. To the best of our knowledge, we are the first to bring user privacy and sentiment fairness into the review generation task. The dataset and source codes are available at https://github.com/ReML-AI/MG-PriFair.
|
|
9. |
- Ait-Mlouk, Addi, et al.
(författare)
-
WINFRA : A Web-Based Platform for Semantic Data Retrieval and Data Analytics
- 2020
-
Ingår i: Mathematics. - : MDPI. - 2227-7390. ; 8:11
-
Tidskriftsartikel (refereegranskat)abstract
- Given the huge amount of heterogeneous data stored in different locations, it needs to be federated and semantically interconnected for further use. This paper introduces WINFRA, a comprehensive open-access platform for semantic web data and advanced analytics based on natural language processing (NLP) and data mining techniques (e.g., association rules, clustering, classification based on associations). The system is designed to facilitate federated data analysis, knowledge discovery, information retrieval, and new techniques to deal with semantic web and knowledge graph representation. The processing step integrates data from multiple sources virtually by creating virtual databases. Afterwards, the developed RDF Generator is built to generate RDF files for different data sources, together with SPARQL queries, to support semantic data search and knowledge graph representation. Furthermore, some application cases are provided to demonstrate how it facilitates advanced data analytics over semantic data and showcase our proposed approach toward semantic association rules.
|
|
10. |
- Banerjee, Sourasekhar, et al.
(författare)
-
Optimized and adaptive federated learning for straggler-resilient device selection
- 2022
-
Ingår i: 2022 International Joint Conference on Neural Networks (IJCNN). - : IEEE. ; , s. 1-9
-
Konferensbidrag (refereegranskat)abstract
- Federated Learning (FL) has evolved as a promising distributed learning paradigm in which data samples are disseminated over massively connected devices in an IID (Identical and Independent Distribution) or non-IID manner. FL follows a collaborative training approach where each device uses local training data to train local models, and the server generates a global model by combining the local model's parameters. However, FL is vulnerable to system heterogeneity when local devices have varying computational, storage, and communication capabilities over time. The presence of stragglers or low-performing devices in the learning process severely impacts the scalability of FL algorithms and significantly delays convergence. To mitigate this problem, we propose Fed-MOODS, a Multi-Objective Optimization-based Device Selection approach to reduce the effect of stragglers in the FL process. The primary criteria for optimization are to maximize: (i) the availability of the processing capacity of each device, (ii) the availability of the memory in devices, and (iii) the bandwidth capacity of the participating devices. The multi-objective optimization prioritizes devices from fast to slow. The approach involves faster devices in early global rounds and gradually incorporating slower devices from the Pareto fronts to improve the model's accuracy. The overall training time of Fed-MOODS is 1.8× and 1.48× faster than the baseline model (FedAvg) with random device selection for MNIST and FMNIST non-IID data, respectively. Fed-MOODS is extensively evaluated under multiple experimental settings, and the results show that Fed-MOODS has significantly improved model's convergence and performance. Fed-MOODS maintains fairness in the prioritized participation of devices and the model for both IID and non-IID settings.
|
|