Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability
Published 1 January 2017Open access
Tiancheng Zhao, Allen Lu, Kyusong Lee, Maxine Eskénazi
Citations85
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This framework enables encoder-decoder models to accomplish slot-value independent decision-making and interact with external databases and shows the flexibility of the proposed method by interleaving chatting capability with a slot-filling system for better out-of-domain recovery.
Abstract
Generative encoder-decoder models offer great promise in developing domaingeneral dialog systems. However, they have mainly been applied to open-domain conversations.
Keywords
Computer Science
Neural ComputationLong Short-Term Memory
98,079 Citations1997Sepp Hochreiter, Jürgen Schmidhuber
A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
UvA-DARE (University of Amsterdam)Adam: A Method for Stochastic Optimization
84,783 Citations2014Diederik P. Kingma, Jimmy Ba
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)
50,318 Citations2021Mandi, Jayanta, Canoy, Rocsildes +2 more
A simple numeric simulation of DNA-co-polymerized hydrogel shape change and a genetic algorithm that generates and selects large batches of material designs that compete with one another to evolve and converge on optimal objective-matching designs are constructed.
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
24,447 Citations2014Kyunghyun Cho, Bart van Merriënboer +5 more
Qualitatively, the proposed RNN Encoder‐Decoder model learns a semantically and syntactically meaningful representation of linguistic phrases.
arXiv (Cornell University)Neural Machine Translation by Jointly Learning to Align and Translate
14,565 Citations2014Dzmitry Bahdanau
Convolutional Neural Networks for Sentence Classification
13,798 Citations2014Yoon Kim
The CNN models discussed herein improve upon the state of the art on 4 out of 7 tasks, which include sentiment analysis and question classification, and are proposed to allow for the use of both task-specific and static vectors.
arXiv (Cornell University)Sequence to Sequence Learning with Neural Networks
13,362 Citations2014Ilya Sutskever, Oriol Vinyals +1 more
Effective Approaches to Attention-based Neural Machine Translation
8,582 Citations2015Thang Luong, Hieu Pham +1 more
A global approach which always attends to all source words and a local one that only looks at a subset of source words at a time are examined, demonstrating the effectiveness of both approaches on the WMT translation tasks between English and German in both directions.
arXiv (Cornell University)Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
7,525 Citations2015Kelvin Xu, Jimmy Ba +6 more
An attention based model that automatically learns to describe the content of images is introduced that can be trained in a deterministic manner using standard backpropagation techniques and stochastically by maximizing a variational lower bound.
Deep Sparse Rectifier Neural Networks
5,408 Citations2012Xavier Glorot, Antoine Bordes +1 more
This paper shows that rectifying neurons are an even better model of biological neurons and yield equal or better performance than hyperbolic tangent networks in spite of the hard non-linearity and non-dierentiabil ity.
International Journal of Data Warehousing and MiningMulti-Label Classification
2,484 Citations2007Grigorios Tsoumakas, Ioannis Katakis
The task of multi-label classification is introduced, the sparse related literature is organizes into a structured presentation and comparative experimental results of certain multilabel classification methods are performed.
arXiv (Cornell University)Recurrent Neural Network Regularization
2,274 Citations2014Wojciech Zaremba, Ilya Sutskever +1 more
This paper shows how to correctly apply dropout to LSTMs, and shows that it substantially reduces overfitting on a variety of tasks.
A Diversity-Promoting Objective Function for Neural Conversation Models
1,986 Citations2016Jiwei Li, Michel Galley +3 more
This work proposes using Maximum Mutual Information (MMI) as the objective function in neural models, and demonstrates that the proposed MMI models produce more diverse, interesting, and appropriate responses, yielding substantive gains in BLEU scores on two conversational datasets and in human evaluations.
Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models
1,725 Citations2016Iulian Vlad Serban, Alessandro Sordoni +3 more
arXiv (Cornell University)Introduction to the CoNLL-2002 Shared Task: Language-Independent Named Entity Recognition
1,574 Citations2002Erik F. Tjong Kim Sang
arXiv (Cornell University)A Neural Conversational Model
1,500 Citations2015Oriol Vinyals, Quoc V. Le
A simple approach to conversational modeling which uses the recently proposed sequence to sequence framework, and is able to extract knowledge from both a domain specific dataset, and from a large, noisy, and general domain dataset of movie subtitles.
arXiv (Cornell University)A Reduction of Imitation Learning and Structured Prediction to No-Regret\n Online Learning
1,313 Citations2010Stéphane Ross, Geoffrey J. Gordon +1 more
Early results for named entity recognition with conditional random fields, feature induction and web-enhanced lexicons
1,161 Citations2003Andrew McCallum, Wei Li
This work has shown that conditionally-trained models, such as conditional maximum entropy models, handle inter-dependent features of greedy sequence modeling in NLP well.
Deep Reinforcement Learning for Dialogue Generation
1,058 Citations2016Jiwei Li, Will Monroe +4 more
This work simulates dialogues between two virtual agents, using policy gradient methods to reward sequences that display three useful conversational properties: informativity, non-repetitive turns, coherence, and ease of answering.
Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
846 Citations2015Tsung-Hsien Wen, Milica Gašić +4 more
A statistical language generator based on a semantically controlled Long Short-term Memory (LSTM) structure that can learn from unaligned data by jointly optimising sentence planning and surface realisation using a simple cross entropy training criterion, and language variation can be easily achieved by sampling from output candidates.
arXiv (Cornell University)A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning
846 Citations2010Stéphane Ross, Geoffrey J. Gordon +1 more
This paper proposes a new iterative algorithm, which trains a stationary deterministic policy, that can be seen as a no regret algorithm in an online learning setting and demonstrates that this new approach outperforms previous approaches on two challenging imitation learning problems and a benchmark sequence labeling problem.
A Network-based End-to-End Trainable Task-oriented Dialogue System
806 Citations2017Tsung-Hsien Wen, David Vandyke +6 more
This work introduces a neural network-based text-in, text-out end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz framework that can converse with human subjects naturally whilst helping them to accomplish tasks in a restaurant search domain.
A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
804 Citations2015Alessandro Sordoni, Michel Galley +7 more
A neural network architecture is used to address sparsity issues that arise when integrating contextual information into classic statistical models, allowing the system to take into account previous dialog utterances.
Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
709 Citations2017Tiancheng Zhao, Ran Zhao +1 more
This work presents a novel framework based on conditional variational autoencoders that capture the discourse-level diversity in the encoder and uses latent variables to learn a distribution over potential conversational intents and generates diverse responses using only greedy decoders.
Dynamic Syntax: The Flow of Language Understanding
370 Citations2000Ruth Kempson, Wilfried Meyer-Viol +1 more
A Syntactic Model of Interpretation of Natural Language as a Formal Language?
Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning
341 Citations2017J. D. Williams, Kavosh Asadi +1 more
This work introduces Hybrid Code Networks (HCNs), which combine an RNN with domain-specific knowledge encoded as software and system action templates, and considerably reduce the amount of training data required, while retaining the key benefit of inferring a latent representation of dialog state.
The Dialog State Tracking Challenge
331 Citations2013J. D. Williams, Antoine Raux +2 more
The dialog state tracking challenge seeks to address this by providing a heterogeneous corpus of 15K human-computer dialogs in a standard format, along with a suite of 11 evaluation metrics, and shows that the suite of performance metrics cluster into 4 natural groups.
Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access
300 Citations2017Bhuwan Dhingra, Lihong Li +5 more
This paper proposes KB-InfoBot - a multi-turn dialogue agent which helps users search Knowledge Bases without composing complicated queries by replacing symbolic queries with an induced “soft” posterior distribution over the KB that indicates which entities the user is interested in.
arXiv (Cornell University)A Diversity-Promoting Objective Function for Neural Conversation Models
253 Citations2015Jiwei Li, Michel Galley +3 more
Let's go public! taking a spoken dialog system to the real world
230 Citations2005Antoine Raux, Brian Langner +3 more
The changes necessary to make the Let’s Go Public spoken dialog system usable for the general public are described and analysis of the calls and strategies used to ensure high performance is presented.
Ravenclaw: dialog management using hierarchical task decomposition and an expectation agenda
199 Citations2003Dan Bohus, Alexander I. Rudnicky
RavenClaw is described, a new dialog management framework developed as a successor to the Agenda architecture used in the CMU Communicator, and allows rapid development of dialog management components for spoken dialog systems operating in complex, goal-oriented domains.
Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning
188 Citations2016Tiancheng Zhao, Maxine Eskénazi
This paper presents an end-to-end framework for task-oriented dialog systems using a variant of Deep Recurrent Q-Networks (DRQN) that is able to interface with a relational database and jointly learn policies for both language understanding and dialog strategy.
Speech CommunicationExample-based dialog modeling for practical multi-domain dialog system
143 Citations2009Cheongjae Lee, Sangkeun Jung +2 more
A generic dialog modeling framework to simultaneously manage goal-oriented and chat dialogs for both information access and entertainment and the system architecture of multi-domain dialog systems using the EBDM framework and the domain spotting technique is introduced.
IEEE Signal Processing MagazineSpoken language understanding
139 Citations2008Renato De Mori, F. Béchet +4 more
Spoken language understanding and natural language understanding share the goal of obtaining a conceptual representation of natural language sentences and computational semantics performs a conceptualization of the world using computational processes for composing a meaning representation structure from available signs.
arXiv (Cornell University)End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning
122 Citations2016J. D. Williams, Geoffrey Zweig
The main component of the model is a recurrent neural network (an LSTM), which maps from raw dialog history directly to a distribution over system actions, which relieves the system developer of much of the manual feature engineering of dialog state.
arXiv (Cornell University)Continuously Learning Neural Dialogue Management
105 Citations2016Pei-Hao Su, Milica Gašić +6 more
A unified neural network framework is proposed to enable the system to first learn by supervision from a set of dialogue data and then continuously improve its behaviour via reinforcement learning, all using gradient-based algorithms on one single model.
USING POMDPS FOR DIALOG MANAGEMENT
98 Citations2006Steve Young
It is explained how partially observable Markov decision processes (POMDPs) can provide a principled mathematical framework for modelling the inherent uncertainty in spoken dialog systems and a form of approximation called the Hidden Information State model which can be used to build practical systems.
Policy committee for adaptation in multi-domain spoken dialogue systems
70 Citations2015M. Gasic, Nikola Mrkšić +4 more
Inspired by Bayesian committee machines, this paper proposes the use of a committee of dialogue policies, and shows that such a model is particularly beneficial for adaptation in multi-domain dialogue systems.
Reference-Aware Language Models
67 Citations2017Zichao Yang, Phil Blunsom +2 more
Experiments on three representative applications show the coreference model variants outperform models based on deterministic attention and standard language modeling baselines.
Distributed dialogue policies for multi-domain statistical dialogue management
59 Citations2015Milica Gašić, D. Kim +2 more
A hierarchical distributed dialogue architecture in which policies are organised in a class hierarchy aligned to an underlying knowledge graph is proposed, which allows a system to be deployed using a modest amount of data to train a small set of generic policies.
Learning Conversational Systems that Interleave Task and Non-Task Content
43 Citations2017Yu Zhou, Alexander I. Rudnicky +1 more
Experiments with human users indicate that a system that interleaves social and task content achieves a better task success rate and is also rated as more engaging compared to a pure task-oriented system.
National Conference on Artificial IntelligenceTickTock: A Non-Goal-Oriented Multimodal Dialog System with Engagement Awareness
37 Citations2015Yu Zhou, Alexandros Papangelis +1 more
Tick, a conversational agent designed to engage humans on topics of its choosing and to carry on an interaction for as long as possible, is described and non-language cues are investigated to create a more robust engagement model based on multiple human communication channels.
arXiv (Cornell University)Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access
36 Citations2016Bhuwan Dhingra, Lihong Li +5 more
Error handling in the RavenClaw dialog management framework
22 Citations2005Dan Bohus, Alexander I. Rudnicky
The key aspects of architectural design which confer task-independence, ease-of-use, adaptability and scalability, and the deployment of this architectture in a number of spoken dialog systems spanning several domains and interaction types are described.
Learning Domain-Independent Dialogue Policies via Ontology Parameterisation
21 Citations2015Zhuoran Wang, Tsung-Hsien Wen +2 more
The experimental results show that the policy optimised in a restaurant search domain using the proposed domain-independent representations can be deployed to a laptop sale domain, achieving a task success rate very close to that of the policy Optimised on in-domain dialogues.
arXiv (Cornell University)Learning Conversational Systems that Interleave Task and Non-Task Content
15 Citations2017Yu Zhou, Alan W. Black +1 more
An Incremental Turn-Taking Model with Active System Barge-in for Spoken Dialog Systems
14 Citations2015Tiancheng Zhao, Alan W. Black +1 more
An incremental turntaking model that provides a novel solution for end-of-turn detection and a systematic procedure of teaching a dialog system to produce meaningful system barge-in that improves system robustness and success rate is presented.
DialPort: A General Framework for Aggregating Dialog Systems
3 Citations2016Tiancheng Zhao, Kyusong Lee +1 more
A new spoken dialog portal that connects systems produced by the spoken dialog research community and gives them access to real users and a prototype dialog framework that affords easy integration with various remote dialog agents as well as external knowledge resources are introduced.