BJBiing-Hwang Juang

Biing-Hwang Juang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Biing-Hwang Juang has a total of 57 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Many Hands Make Light Work: Task-Oriented Dialogue System with Module-Based Mixture-of-Experts

    by Ruolin Su, Biing-Hwang Juang

    Task-oriented dialogue systems are broadly used in virtual assistants and other automated services, providing interfaces between users and machines to facilitate specific tasks. Nowadays, task-oriented dialogue systems have greatly benefited from pre-trained language models (PLMs). However, their task-solving performance is constrained by the inherent capacities of PLMs, and scaling these models is expensive and complex as the model size becomes larger. To address these challenges, we propose Soft Mixture-of-Expert Task-Oriented Dialogue system (SMETOD) which leverages an ensemble of Mixture-of-Experts (MoEs) to excel at subproblems and generate specialized outputs for task-oriented dialogues. SMETOD also scales up a task-oriented dialogue system with simplicity and flexibility while maintaining inference efficiency. We extensively evaluate our model on three benchmark functionalities: intent prediction, dialogue state tracking, and dialogue response generation. Experimental results demonstrate that SMETOD achieves state-of-the-art performance on most evaluated metrics. Moreover, comparisons against existing strong baselines show that SMETOD has a great advantage in the cost of inference and correctness in problem-solving.

  • Accretionary Learning With Deep Neural Networks With Applications

    by Xinyu Wei, Biing-Hwang Fred Juang, Ouya Wang, Shenglong Zhou, Geoffrey Ye Li

    One of the fundamental limitations of Deep Neural Networks (DNN) is their inability to acquire and accumulate new cognitive capabilities in an incremental or progressive manner. When data appear from object classes not among the learned ones, a conventional DNN would not be able to recognize them due to the fundamental formulation that it assumes. A typical solution is to re-design and re-learn a new network, most likely an expanded one, for the expanded set of object classes. This process is quite different from that of a human learner. In this paper, we propose a new learning method named Accretionary Learning (AL) to emulate human learning, in that the set of object classes to be recognized need not be fixed, meaning it can grow as the situation arises without requiring an entire redesign of the system. The proposed learning structure is modularized, and can dynamically expand to learn and register new knowledge, as the set of objects grows in size. AL does not forget previous knowledge when learning new data classes. We show that the structure and its learning methodology lead to a system that can grow to cope with increased cognitive complexity while providing stable and superior overall performance.


  • Open Access

    Schema Graph-Guided Prompt for Multi-Domain Dialogue State Tracking

    by Ruolin Su, Ting-Wei Wu, Biing-Hwang Juang

    Tracking dialogue states is an essential topic in task-oriented dialogue systems, which involve filling in the necessary information in pre-defined slots corresponding to a schema. While general pre-trained language models have been shown effective in slot-filling, their performance is limited when applied to specific domains. We propose a graph-based framework that learns domain-specific prompts by incorporating the dialogue schema. Specifically, we embed domain-specific schema encoded by a graph neural network into the pre-trained language model, which allows for relations in the schema to guide the model for better adaptation to the specific domain. Our experiments demonstrate that the proposed graph-based method outperforms other multi-domain DST approaches while using similar or fewer trainable parameters. We also conduct a comprehensive study of schema graph architectures, parameter usage, and module ablation that demonstrate the effectiveness of our model on multi-domain dialogue state tracking.

  • Open Access

    Choice Fusion as Knowledge for Zero-Shot Dialogue State Tracking

    by Ruolin Su, Jingfeng Yang, Ting-Wei Wu, Biing-Hwang Juang

    With the demanding need for deploying dialogue systems in new domains with less cost, zero-shot dialogue state tracking (DST), which tracks user's requirements in task-oriented dialogues without training on desired domains, draws attention increasingly. Although prior works have leveraged question-answering (QA) data to reduce the need for in-domain training in DST, they fail to explicitly model knowledge transfer and fusion for tracking dialogue states. To address this issue, we propose CoFunDST, which is trained on domain-agnostic QA datasets and directly uses candidate choices of slot-values as knowledge for zero-shot dialogue-state generation, based on a T5 pre-trained language model. Specifically, CoFunDST selects highly-relevant choices to the reference context and fuses them to initialize the decoder to constrain the model outputs. Our experimental results show that our proposed model achieves outperformed joint goal accuracy compared to existing zero-shot DST approaches in most domains on the MultiWOZ 2.1. Extensive analyses demonstrate the effectiveness of our proposed approach for improving zero-shot DST learning from QA.

  • Open Access

    Infusing Context and Knowledge Awareness in Multi-turn Dialog Understanding

    by Ting-Wei Wu, Biing-Hwang Juang

    Ting-Wei Wu, Biing-Hwang Juang. Findings of the Association for Computational Linguistics: EACL 2023. 2023.

  • Open Access

    Towards Zero-Shot Multilingual Transfer for Code-Switched Responses

    by Ting-Wei Wu, Changsheng Zhao, Ernie Chang, Yangyang Shi, Pierce Chuang, Vikas Chandra, Biing Juang

    Ting-Wei Wu, Changsheng Zhao, Ernie Chang, Yangyang Shi, Pierce Chuang, Vikas Chandra, Biing Juang. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.


  • Open Access

    A Context-Aware Hierarchical BERT Fusion Network for Multi-turn Dialog Act Detection

    by Ting-Wei Wu, Ruolin Su, Biing-Hwang Juang

    The success of interactive dialog systems is usually associated with the quality of the spoken language understanding (SLU) task, which mainly identifies the corresponding dialog acts and slot values in each turn. By treating utterances in isolation, most SLU systems often overlook the semantic context in which a dialog act is expected. The act dependency between turns is non-trivial and yet critical to the identification of the correct semantic representations. Previous works with limited context awareness have exposed the inadequacy of dealing with complexity in multiproned user intents, which are subject to spontaneous change during turn transitions. In this work, we propose to enhance SLU in multi-turn dialogs, employing a context-aware hierarchical BERT fusion Network (CaBERT-SLU) to not only discern context information within a dialog but also jointly identify multiple dialog acts and slots in each utterance. Experimental results show that our approach reaches new state-of-the-art (SOTA) performances in two complicated multi-turn dialogue datasets with considerable improvements compared with previous methods, which only consider single utterances for multiple intents and slot filling.


  • Open Access

    Deep Learning Enabled Semantic Communication Systems

    by Huiqiang Xie, Zhijin Qin, Geoffrey Ye Li, Biing-Hwang Juang

    Recently, deep learned enabled end-to-end (E2E) communication systems have been developed to merge all physical layer blocks in the traditional communication systems, which make joint transceiver optimization possible. Powered by deep learning, natural language processing (NLP) has achieved great success in analyzing and understanding large amounts of language texts. Inspired by research results in both areas, we aim to providing a new view on communication systems from the semantic level. Particularly, we propose a deep learning based semantic communication system, named DeepSC, for text transmission. Based on the Transformer, the DeepSC aims at maximizing the system capacity and minimizing the semantic errors by recovering the meaning of sentences, rather than bit- or symbol-errors in traditional communications. Moreover, transfer learning is used to ensure the DeepSC applicable to different communication environments and to accelerate the model training process. To justify the performance of semantic communications accurately, we also initialize a new metric, named sentence similarity. Compared with the traditional communication system without considering semantic information exchange, the proposed DeepSC is more robust to channel variation and is able to achieve better performance, especially in the low signal-to-noise (SNR) regime, as demonstrated by the extensive simulation results.

  • Top Cited Papers
    Open Access

    Deep Learning Enabled Semantic Communication Systems

    by Huiqiang Xie, Zhijin Qin, Geoffrey Ye Li, Biing-Hwang Juang

    Recently, deep learned enabled end-to-end (E2E) communication systems have been developed to merge all physical layer blocks in the traditional communication systems, which make joint transceiver optimization possible. Powered by deep learning, natural language processing (NLP) has achieved great success in analyzing and understanding a large amount of language texts. Inspired by research results in both areas, we aim to provide a new view on communication systems from the semantic level. Particularly, we propose a deep learning based semantic communication system, named DeepSC, for text transmission. Based on the Transformer, the DeepSC aims at maximizing the system capacity and minimizing the semantic errors by recovering the meaning of sentences, rather than bit-or symbol-errors in traditional communications. Moreover, transfer learning is used to ensure the DeepSC applicable to different communication environments and to accelerate the model training process. To justify the performance of semantic communications accurately, we also initialize a new metric, named sentence similarity. Compared with the traditional communication system without considering semantic information exchange, the proposed DeepSC is more robust to channel variation and is able to achieve better performance, especially in the low signal-to-noise (SNR) regime, as demonstrated by the extensive simulation results.


  • Deep Learning Based End-to-End Wireless Communication Systems Without Pilots

    by Hao Ye, Geoffrey Ye Li, Biing-Hwang Juang

    The recent development in machine learning, especially in deep neural networks (DNN), has enabled learning-based end-to-end communication systems, where DNNs are employed to substitute all modules at the transmitter and receiver. In this article, two end-to-end frameworks for frequency-selective channels and multi-input and multi-output (MIMO) channels are developed, where the wireless channel effects are modeled with an untrainable stochastic convolutional layer. The end-to-end framework is trained with mini-batches of input data and channel samples. Instead of using pilot information to implicitly or explicitly estimate the unknown channel parameters as in current communication systems, the transmitter DNN learns to transform the input data in a way that is robust to various channel conditions. The receiver consists of two DNN modules used for channel information extraction and data recovery, respectively. A bilinear production operation is employed to combine the features extracted from the channel information extraction module and the received signals. The combined features are further utilized in the data recovery module to recover the transmitted data. Compared with the conventional communication systems, performance improvement has been shown for frequency-selective channels and MIMO channels. Furthermore, the end-to-end system can automatically leverage the correlation in the channels and in the source data to improve the overall performance.