skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

A Multi-Attention Approach Using BERT and Stacked Bidirectional LSTM for Improved Dialogue State Tracking

Applied sciences, 2023-02, Vol.13 (3), p.1775 [Peer Reviewed Journal]

2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;ISSN: 2076-3417 ;EISSN: 2076-3417 ;DOI: 10.3390/app13031775

Full text available

Citations Cited by
  • Title:
    A Multi-Attention Approach Using BERT and Stacked Bidirectional LSTM for Improved Dialogue State Tracking
  • Author: Khan, Muhammad Asif ; Huang, Yi ; Feng, Junlan ; Prasad, Bhuyan Kaibalya ; Ali, Zafar ; Ullah, Irfan ; Kefalas, Pavlos
  • Subjects: attention mechanism ; BERT ; Classification ; classification problem ; Datasets ; dialogue state tracking ; Feature extraction ; Interactive computer systems ; Language ; Natural language ; Neural networks ; Ontology ; Semantics ; Speech ; spoken dialogue systems ; stacked BiLSTM ; Verbal communication
  • Is Part Of: Applied sciences, 2023-02, Vol.13 (3), p.1775
  • Description: The modern digital world and associated innovative and state-of-the-art applications that characterize its presence, render the current digital age a captivating era for many worldwide. These innovations include dialogue systems, such as Apple’s Siri, Google Now, and Microsoft’s Cortana, that stay on the personal devices of users and assist them in their daily activities. These systems track the intentions of users by analyzing their speech, context by looking at their previous turns, and several other external details, and respond or act in the form of speech output. For these systems to work efficiently, a dialogue state tracking (DST) module is required to infer the current state of the dialogue in a conversation by processing previous states up to the current state. However, developing a DST module that tracks and exploit dialogue states effectively and accurately is challenging. The notable challenges that warrant immediate attention include scalability, handling the unseen slot-value pairs during training, and retraining the model with changes in the domain ontology. In this article, we present a new end-to-end framework by combining BERT, Stacked Bidirectional LSTM (BiLSTM), and a multiple attention mechanism to formalize DST as a classification problem and address the aforementioned issues. The BERT-based module encodes the user’s and system’s utterances. The Stacked BiLSTM extracts the contextual features and multiple attention mechanisms to calculate the attention between its hidden states and the utterance embeddings. We experimentally evaluated our method against the current approaches over a variety of datasets. The results indicate a significant overall improvement. The proposed model is scalable in terms of sharing the parameters and it considers the unseen instances during training.
  • Publisher: Basel: MDPI AG
  • Language: English
  • Identifier: ISSN: 2076-3417
    EISSN: 2076-3417
    DOI: 10.3390/app13031775
  • Source: DOAJ Directory of Open Access Journals
    ROAD
    ProQuest Central
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait