SEQ2SEQ++: A Multitasking-Based Seq2seq Model to Generate Meaningful and Relevant Answers

Palasundram, Kulothunkan; Sharef, Nurfadhlina Mohd; Kasmiran, Khairul Azhar; Azman, Azreen

doi:10.1109/access.2021.3133495

Cited by 11 publications

(4 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, the GRU model is easy for training and the efficiency can be greatly improved. Hence, GRU structure is greatly used in natural language processing [39] and feature classification [40]. It has been also used in traffic condition estimation [41] and car-following behavior [8].…”

Section: Methodology a Preliminaries 1) Seq2seq Modelmentioning

confidence: 99%

Learning Car-Following Behaviors for a Connected Automated Vehicle System: An Improved Sequence-to-Sequence Deep Learning Model

Liang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Data-driven car-following modeling is of great significance to traffic behavior analysis and the development of connected automated vehicle (CAV) technology. The existing researches focus on reproducing the car-following process by capturing the behavior of the host vehicle using the information of its nearest preceding vehicle. While the other preceding vehicles may affect the host vehicle as well. To fill the gap above, this paper presents an improved sequence-tosequence deep learning-based (ISDL) car-following model for a CAV system. Firstly, the kinematics information considering the multiple preceding vehicles are organized as the input characteristics. Secondly, an improved sequence-to-sequence deep learning framework is proposed by integrating an encoder with the bidirectional gated recurrent unit (GRU) neural network and a decoder using an attention-based GRU neural network in an end-to-end fashion. Finally, the car-following data with multiple preceding vehicles captured from the NGSIM dataset are employed to train and calibrate the proposed model. Experimental results indicate that the deep learning-based models' performance in learning heterogeneous driving behavior can be enhanced by adding information about multiple preceding vehicles. In addition, the proposed ISDL model outperforms the benchmark car-following models in terms of the accuracy of the simulated speeds and simulated positions. Through tests on platoon simulation, the ISDL model is capable of reshaping the traffic oscillation phenomenon as well.INDEX TERMS Car-following modeling; improved sequence-to-sequence model; information flow topology; gated recurrent unit neural network; connected automated vehicle

show abstract

Section: Methodology a Preliminaries 1) Seq2seq Modelmentioning

confidence: 99%

Learning Car-Following Behaviors for a Connected Automated Vehicle System: An Improved Sequence-to-Sequence Deep Learning Model

Liang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Cai, Tian, Kazemnejad and et al [6], [7], [43] treat the retrieval and generation as disjointed components and train them separately, but this means additional data is needed. Multi-task learning that jointly optimize retrieval and generation steps are also explored [44]. Unlike other studies that largely focus on improving the generation component, Wu et al [45] propose improving the performance of the retrieval component through entity alignment.…”

Section: Related Workmentioning

confidence: 99%

Open Domain Response Generation Guided by Retrieved Conversations

Chen

Zhang²,

Chen³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Open domain response generation is the task of creating a response given a user query in any topics/domain. Limited by context and reference information, responses generated by current systems are often "bland" or generic. In this paper, we combine a response generation model with a retrieval system that searches for relevant utterances and responses. The generation model has two main components: a keyword extraction module and a two-stage transformer. The keyword extraction module aims to extract two types of keywords in an unsupervised fashion from the retrieved results: (1) keywords in the query not found in the retrieved utterances (DiffKey), and (2) overlapping keywords among the retrieved responses (SimKey). Given these keywords, the two-stage transformer first decides where to insert the keywords in the response, and the second generates the full response given the location of the keywords. The keyword extraction module and the two-stage transformer are connected in a single network, and so our system is trained end-to-end. Experimental results on Cornell Movie-Dialog corpus, Douban and Weibo demonstrate that our model outperforms state-of-the-art systems in terms of ROUGE, relevance scores and human evaluation.

show abstract

“…Some attempts have been made to improve model efficiency and implement multiple processes by building multiple models or deploying multi-task learning (MTL) in neural networks [27], [28]. In recent years, there has been an increasing amount of studies describing the applications of MTL in various domains including Natural Language Processing (NLP) [18], [19] and computer vision [23], [29] to allow the model to share low level features, thereby improving the achievement of task objectives. However, improvement is needed for their application to parallel processing which requires more independent analysis rather than correlations for sub-group behavior analysis.…”

Section: Related Workmentioning

confidence: 99%

Transformation based Parallel Forecasting of Individual Gas Consumption from Smart Meter Data

Hu¹,

Sikdar²

2023

Preprint

View full text Add to dashboard Cite

<p>The prediction of energy consumption of users is an important requirement for utilities. Machine learning using neural networks has been applied for predicting household energy consumption due to effectiveness in capturing correlations and patterns. However, the result is predicted by learning over the behavior of the training data as a whole and ignoring the differences between sub-group behavior (i.e., groups of users with similar characteristics). The prediction of energy consumption of users is an important requirement for utilities. Exploiting the behavioral differences between different subgroups in the population can improve the system’s capability to perform parallel processing of similar tasks. This paper proposes an innovative model to simultaneously predict gas consumption of multiple households or population subgroups. The proposed method is based on the use of data transformations and focuses on differences in individual behavior. The evaluation of the model is discussed from three aspects: prediction accuracy, risk of privacy, as well as system robustness. The results shows that the proposed system can achieve multiple prediction simultaneously with reasonable accuracy and be secure against noise and attacks on private information. </p>

show abstract

SEQ2SEQ++: A Multitasking-Based Seq2seq Model to Generate Meaningful and Relevant Answers

Abstract: Date of publication xxxx 00, 0000, date of current version xxxx 00, 0000.

Cited by 11 publications

References 42 publications

Learning Car-Following Behaviors for a Connected Automated Vehicle System: An Improved Sequence-to-Sequence Deep Learning Model

Learning Car-Following Behaviors for a Connected Automated Vehicle System: An Improved Sequence-to-Sequence Deep Learning Model

Open Domain Response Generation Guided by Retrieved Conversations

Transformation based Parallel Forecasting of Individual Gas Consumption from Smart Meter Data

Contact Info

Product

Resources

About