Deep Neural Network Approach for the Dialog State Tracking Challenge

By Matthew Henderson, Blaise Thomson, Susannah Young. 2013

164 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

A Simple Language Model for Task-Oriented Dialogue (2020, background): “These components include understanding user intent via intent detection [26], tracking the constraints imposed by the user via dialogue state tracking [20, 32, 41, 34, 53, 59, 64, 8, 19], determining system actions via dialogue policy [51], and using dedicated response generation components [49].”
Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models (2015, background): “y a real dialogue system, but also limits its usage to a narrow domain. Recent work has tried to push goal driven systems towards learning the observed features themselves with neural network models (Henderson et al., 2013; Henderson et al., 2014), yet such approaches still require large corpora of ”
Neural Approaches to Conversational AI (2018, neutral): “m data by statistical learning algorithms like conditional random ﬁelds (Henderson, 2015). More recently, neural approaches have started to gain popularity, with applications of deep neural networks (Henderson et al., 2013) and recurrent networks (Mrkˇsi ´c et al., 2015) as some of the early example”
A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version (2015, background): “For example, Henderson et al. (2013) proposed to use a feed-forward neural network.”
Generative Deep Neural Networks for Dialogue: A Short Review (2016, background): “…investigated applying neural networks to the different components of a standard dialogue system, including natural language understanding, natural language generation, dialogue state tracking and evaluation [Wen et al., 2016, 2015, Henderson et al., 2013, Mrkši´c et al., 2015, Su et al., 2015].”
Deep Learning: Methods and Applications (2014, background): “to emotion recognition from speech in [207, 222], to spoken language understanding in [242, 366, 403], to speaker recognition in [351, 372], to language-type recognition in [112], to dialogue state tracking for spoken dialogue systems in [94, 152], to automatic voice activity detection in [442], to ”
MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling (2018, methodology): “…led to the same solution of using statistical framework and machine learning for various sys-tem components, such as natural language understanding (Henderson et al., 2013; Mesnil et al., 2015; Mrkˇsi´c et al., 2017a), dialogue management (Gaˇsi´c and Young, 2014; Tegho et al., 2018), language…”
Word-Based Dialog State Tracking with Recurrent Neural Networks (2014, methodology): “Proceedings of the SIGDIAL 2014 Conference, pages 292–299, Philadelphia, U.S.A., 18-20 June 2014. c©2014 Association for Computational Linguistics”
Challenges in Building Intelligent Open-domain Dialog Systems (2019, background): “e user [47,145,152]. 2A task schema typically defines a set of user intents, and for each intent defines a set of dialog acts, slot-value pairs. 3Dialog management performs both dialog state tracking [42,81] and response selection via policy [64,91,123,172]. 4Recently, there are end-to-end methods [”
A Survey on Dialogue Systems: Recent Advances and New Frontiers (2017, background): “of handcrafted rules [80], conditional random ﬁelds [28; 27; 53], maximum entropy models [85] and web-style ranking [88] have emerged in Dialog State Tracking Challenge (DSTC) shared tasks. Recently, [20] introduced deep learning in belief tracking. It used a sliding window to output a sequence of p”
Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset (2019, methodology): “In a departure from traditional annotation techniques (Henderson et al., 2013; Rojas-Barahona et al., 2017; Budzianowski et al., 2018), dialogs are labeled with simple API calls and arguments.”
Domain Adaptive Dialog Generation via Meta Learning (2019, background): “Henderson et al. (2013) introduces the concept of belief tracker that tracks users’ requirements and constraints in the dialog across turns.”
Survey on evaluation methods for dialogue systems (2019, methodology): “ Methods for Dialogue Systems 39 Name Topics # dialogues Reference DSTC1 Bus schedules 15,000 (Williams et al., 2013) DSTC2 Restaurants 3,000 (Henderson et al., 2014) DSTC3 Tourist information 2,265 (Henderson et al., 2013a) DSTC4 & DSTC5 Tourist information 35 (Kim et al., 2016) DSTC6 Restauran”
The third Dialog State Tracking Challenge (2014, background): “Entries to these challenges broke new ground in dialog state tracking, including the use of conditional random fields [3, 4, 5], sophisticated and robust hand-crafted rules [6], neural networks and recurrent neural networks [7, 8], multidomain learning [9], and web-style ranking [10].”
Scalable multi-domain dialogue state tracking (2017, methodology): “…represents the system’s estimate of the user’s goal given the conversation history and is used (1) to make calls to an API, database or action provider based on the user’s preferences speciﬁed during the dialogue (2) as an input to the dialogue policy [1, 2] which predicts the next system response.”
A Theoretical Framework for Conversational Search (2017, background): “During such a conversation, even if the user’s search task does not change their understanding of the task, their query vocabulary may change and they may apply a variety of search strategies [2].”
Incorporating Unstructured Textual Knowledge Sources into Neural Dialogue Systems (2015, background): “Several recent results have shown that neural networks provide powerful models for various modules of spoken dialogue systems, from speech recognition [4, 5], to state tracking [7] and natural language generation [19].”