Hybrid Dialogue State Tracking for Real World Human-to-Human Dialogues

Sun, Kai; Zhu, Su; Chen, Lü; Yao, Siqiu; Wu, Xueyang; Yu, Kai

doi:10.21437/interspeech.2016-949

Cited by 6 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A various of models are proposed, e.g. rule-based models (Wang and Lemon, 2013;Sun et al, 2014a;Yu et al, , 2016Sun et al, 2016b), generative statistical models Young et al, , 2013, and discriminative statistical models (Lee and Eskenazi, 2013;Lee, 2013;Sun et al, 2014b;Xie et al, 2015;Sun et al, 2016a;Xie et al, 2018). And the state-of-the-art one is the deep learning-based approach.…”

Section: Introductionmentioning

confidence: 99%

Towards Universal Dialogue State Tracking

Ren¹,

Xie²,

Chen³

et al. 2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Self Cite

122

View full text Add to dashboard Cite

Dialogue state tracking is the core part of a spoken dialogue system. It estimates the beliefs of possible user's goals at every dialogue turn. However, for most current approaches, it's difficult to scale to large dialogue domains. They have one or more of following limitations: (a) Some models don't work in the situation where slot values in ontology changes dynamically; (b) The number of model parameters is proportional to the number of slots; (c) Some models extract features based on hand-crafted lexicons. To tackle these challenges, we propose StateNet, a universal dialogue state tracker. It is independent of the number of values, shares parameters across all slots, and uses pre-trained word vectors instead of explicit semantic dictionaries. Our experiments on two datasets show that our approach not only overcomes the limitations, but also significantly outperforms the performance of state-of-the-art approaches.

show abstract

Section: Introductionmentioning

confidence: 99%

Towards Universal Dialogue State Tracking

Ren¹,

Xie²,

Chen³

et al. 2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Self Cite

122

View full text Add to dashboard Cite

show abstract

“…The straightforward possibility relies on applying a rule-based model in parallel with the SL model and taking the outputs union of both as a final dialogue state. The hybrid DST model proposed by [106] is an example of such approach which rely…”

Section: Hybrid Approachesmentioning

confidence: 99%

“…Frame-Based: [37], [36], Amazon Alexa, Google actions, DialogFlow; SL-based: [40], [41], [42], [44], [45], [39], [43], [46], [47], [55], [3], [49], [62]; RL-based: [88], [93], [92], [79], [105], [82], [89], [90], [77], [72], [76], [78], [75], [27], [83], [80], [81] ; Hybrid: [106], [107], [108], [54], [109], [110] User profile rule-based: [15], [18]; FSM-Based: [32]; Activity-based: ManyChat, Chatfuel and FlowXO; Frame-Based: [37], [36], Amazon Alexa, Google actions, DialogFlow;…”

Section: Conversation Historymentioning

confidence: 99%

Dialogue Management in Conversational Systems: A Review of Approaches, Challenges, and Opportunities

Brabra

Báez

Benatallah

et al. 2022

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

Attracted by their easy-to-use interfaces and captivating benefits, conversational systems have been widely embraced by many individuals and organizations as side-by-side digital co-workers. They enable the understanding of user needs, expressed in natural language, and on fulfilling such needs by invoking the appropriate backend services (e.g., APIs). Controlling the conversation flow, known as Dialogue Management, is one of the essential tasks in conversational systems and the key to its success and adoption as well. Nevertheless, designing scalable and robust dialogue management techniques to effectively support intelligent conversations remains a deeply challenging problem. This article studies dialogue management from an in-depth design perspective. We discuss the state of the art approaches, identify their recent advances and challenges, and provide an outlook on future research directions. Thus, we contribute to guiding researchers and practitioners in selecting the appropriate dialogue management approach aligned with their objectives, among the variety of approaches proposed so far.

show abstract

“…Most research on goal-oriented dialogue has focused almost exclusively on dialogue state tracking and dialogue policy learning (Sun et al, 2014(Sun et al, , 2016Li et al, 2017b;Henderson, 2015;Henderson et al, 2014;Rastogi et al, 2017;Mrkšić et al, 2016;Yoshino et al, 2016). Dialogue state tracking consists of detecting the user intent and tends to rely on turn-level supervision and a preset number of possible slot and value pairs which limits the flexibility of such chatbots, including their ability to respond to informal chit chat, as well as transferring knowledge across domains.…”

Section: Related Workmentioning

confidence: 99%

Retrieval-based Goal-Oriented Dialogue Generation

Gonzalez¹,

Augenstein²,

Søgaard³

2019

Preprint

View full text Add to dashboard Cite

Most research on dialogue has focused either on dialogue generation for openended chit chat or on state tracking for goal-directed dialogue. In this work, we explore a hybrid approach to goal-oriented dialogue generation that combines retrieval from past history with a hierarchical, neural encoder-decoder architecture. We evaluate this approach in the customer support domain using the Multiwoz dataset (Budzianowski et al., 2018). We show that adding this retrieval step to a hierarchical, neural encoder-decoder architecture leads to significant improvements, including responses that are rated more appropriate and fluent by human evaluators. Finally, we compare our retrieval-based model to various semantically conditioned models explicitly using past dialog act information, and find that our proposed model is competitive with the current state of the art (Chen et al., 2019), while not requiring explicit labels about past machine acts.Preprint. Under review.

show abstract

Hybrid Dialogue State Tracking for Real World Human-to-Human Dialogues

Cited by 6 publications

References 9 publications

Towards Universal Dialogue State Tracking

Towards Universal Dialogue State Tracking

Dialogue Management in Conversational Systems: A Review of Approaches, Challenges, and Opportunities

Retrieval-based Goal-Oriented Dialogue Generation

Contact Info

Product

Resources

About