A Network-based End-to-End Trainable Task-oriented Dialogue System

By Lina Maria Rojas-Barahona, Milica Gasic, Nikola Mrksic, Pei-hao Su, Stefan Ultes, Tsung-Hsien Wen, Susannah Young, David Vandyke. 2016

1,155 citations recorded by the source corpus.

Teaching machines to accomplish tasks by conversing naturally with humans is challenging. Currently, developing task-oriented dialogue systems requires creating multiple components and typically this involves either a large amount of handcrafting, or acquiring costly labelled datasets to solve a statistical learning problem for each component. In this work we introduce 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. This approach allows us to develop dialogue systems easily and without making too many assumptions about the task at hand. The results show that the model can converse with human subjects naturally whilst helping them to accomplish tasks in a restaurant search domain.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

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

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

The Natural Language Decathlon: Multitask Learning as Question Answering (2018, methodology): “Oz (WOZ) restaurant reservation task [Wen et al., 2016], which comes with a predefined ontology of foods, dates, times, addresses, and other information that would help an agent make a reservation for a customer.”
Ethical and social risks of harm from Language Models (2021, background): “We refer to such systems as “conversational agents” (CAs) (Perez-Marin and PascualNieto, 2011); they are also known as “dialogue systems” in the literature (Wen et al., 2017).”
Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions (2020, background): “Human Evaluations Goal-oriented dialogue systems often have clear evaluation methodologies, e.g. task completion can be measured if the correct actions are taken (Hastie, 2012; Henderson, Thomson, and Williams, 2014; Bordes, Boureau, and Weston, 2017; El Asri et al., 2017; Wen et al., 2017).”
ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisons (2019, background): “Goal-oriented tasks typically have a clearer evaluation, e.g. task completion can be measured if the correct actions are taken (Hastie 2012; Henderson, Thomson, and Williams 2014; Bordes, Boureau, and Weston 2017; El Asri et al. 2017; Wen et al. 2017).”
Towards Exploiting Background Knowledge for Building Conversation Systems (2018, background): “direction (Rojas-Barahona et al., 2017; Williams et al., 2016; Lowe et al., 2015a; Ghazvininejad et al., 2017) which try to integrate external knowledge sources with existing datasets, we believe that building new datasets where the utterances are”
Efficient Natural Language Response Suggestion for Smart Reply (2017, background): “In recent work, the components of task-oriented dialog systems have been implemented as neural networks, enabling joint learning of robust models [7, 26, 27].”
Learning Through Dialogue Interactions (2016, background): “It also include a collection of goal-oriented dialogue systems (Wen et al., 2016; Su et al., 2016; Bordes & Weston, 2016), which complete a certain task such as booking a ticket or making a reservation at a restaurant.”
A Simple Language Model for Task-Oriented Dialogue (2020, background): “The pipeline requires natural language understanding (NLU) for belief state tracking, dialogue management (DM) for deciding which actions to take based on those beliefs, and natural language generation (NLG) for generating responses [50].”
Surprising Negative Results for Generative Adversarial Tree Search (2018, background): “For example (Cuayáhuitl, 2016; Fatemi et al., 2016; Wen et al., 2016) investigate DRL for dialogue policy learning, with (Lipton et al., 2018) addressing the efﬁciency of exploration.”
Deep Reinforcement Learning for Dialogue Generation (2016, background): “We are thus particularly inspired by recent work that attempts to merge these paradigms, including Wen et al. (2016)— training an end-to-end task-oriented dialogue system that links input representations to slot-value pairs in a database— or Su et al. (2016), who combine reinforcement learning with…”
Neural Approaches to Conversational AI (2018, neutral): “The first is based on supervised learning, where desired system responses are first collected and then used to train multiple components of a dialogue system in order to maximize prediction accuracy (Bordes et al., 2017; Wen et al., 2017; Yang et al., 2017b; Eric et al., 2017; Madotto et al., 2018; ”
What makes a good conversation? How controllable attributes affect human judgments (2019, background): “Dialogue Dialogue evaluation is relatively well understood in goal-oriented tasks, where automated approaches can be coded by measuring task completion (Bordes et al., 2017; El Asri et al., 2017; Hastie, 2012; Henderson et al., 2014; Wen et al., 2017).”
A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version (2015, background): “Neural networks can be applied to narrow domains, such as restaurant recommendation, with relatively little data (Wen et al., 2017).”
Training Millions of Personalized Dialogue Agents (2018, background): “…dialogue systems, based on neural architectures like bidirectional LSTMs or Memory Networks (Sukhbaatar et al., 2015) trained directly by gradient descent on dialogue logs, have been showing promising performance in multiple contexts (Wen et al., 2016; Serban et al., 2016; Bordes et al., 2016).”
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].”
Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge (2019, methodology): “We focus on restaurant recommendations in our experiments, which, previously, have been widely explored in dialogue systems research, e.g. (Young et al. 2010; Henderson, Thomson, and Williams 2014; Wen et al. 2017).”
Lifelong and Continual Learning Dialogue Systems: Learning during Conversation (2021, background): “(2) Task-oriented chatbots (Williams and Young 2007; Wen et al. 2017) designed to assist users to complete tasks based on users’ requests, e.”