Let's go public! taking a spoken dialog system to the real world

By Antoine Raux, Brian Langner, Dan Bohus, Alan W. Black, Maxine Eskénazi. 2005

296 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Dialogue & Conversational AI, Speech & Audio

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 Information Systems

In Dialogue & Conversational AI

In Speech & Audio

Citations in the corpus

A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version (2015, background): “For example, in the Let’s Go! dialogue system (Raux et al., 2005), the user requests information about various bus arrival and departure times.”
The Second Dialog State Tracking Challenge (2014, background): “However, differences between these two user groups have been shown (Raux et al., 2005), so future studies should also test on real users.”
Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings (2016, methodology): “Unlike most previous NLG systems for SDS (e.g., (Stent et al., 2004; Raux et al., 2005; Mairesse et al., 2010)), it is trainable from unaligned pairs of MR and sentences alone.”
MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling (2018, background): “One famous example of this kind is the Let’s Go Bus Information System which offers live bus schedule information over the phone (Raux et al., 2005) leading to the ﬁrst Di-alogue State Tracking Challenge (Williams et al., 2013).”
Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems (2018, background): “Conventional task-oriented dialogue systems have a complex pipeline (Rudnicky et al., 1999; Raux et al., 2005; Young et al., 2013) consisting of independently developed and modularly connected components for natural language understanding (NLU) (Mesnil et al.”
Iterative policy learning in end-to-end trainable task-oriented neural dialog models (2017, background): “Conventional task-oriented dialog systems are designed with complex pipelines [4, 5, 6, 7], and there are usually separately developed modules for natural language understanding (NLU) [8, 9, 10, 11], dialog state tracking (DST) [12, 13], and dialog management (DM) [14, 15, 16].”
Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning (2016, background): “Task-oriented dialog systems have been an important branch of spoken dialog system (SDS) research (Raux et al., 2005; Young, 2006; Bo-hus and Rudnicky, 2003).”
The Rapidly Changing Landscape of Conversational Agents (2018, background): “Later, this was opened to the general public (Raux et al, 2005 [10]).”
Alex: Bootstrapping a Spoken Dialogue System for a New Domain by Real Users (2014, background): “Let’s Go (Raux et al., 2005; Raux et al., 2006) is a notable example in the public transportation domain.”
Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders (2017, methodology): “For example, dialog acts (Poesio and Traum, 1998) have been widely used in the dialog managers (Lit-man and Allen, 1987; Raux et al., 2005; Zhao and Eskenazi, 2016) to represent the propositional function of the system.”
Lexical and Syntactic Adaptation and Their Impact in Deployed Spoken Dialog Systems (2009, methodology): “We analyze dialogs from CMU’s Let’s Go! dialog system (Raux et al., 2005).”
A survey on empathetic dialogue systems (2020, background): “[49] TI,ST EA+EE VAD Tweets Word Embedding;Reinforcement-VAE Shi and Yu [50] TO,MT EA+EE Multimodal DSTC-1 [51] Policy learning Huang et al.”
Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability (2017, background): “Task-oriented spoken dialog systems have transformed human-computer interaction by enabling people interact with computers via spoken language (Raux et al., 2005; Young, 2006; Bohus and Rudnicky, 2003).”
Hierarchical Pointer Memory Network for Task Oriented Dialogue (2018, background): “Some examples include restaurant reservation (Henderson et al., 2014), movie ticket booking (Li et al., 2017) and bus information system (Raux et al., 2005).”
Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models (2019, background): “For traditional modular systems, the action space is defined by hand-crafted semantic representations such as dialog acts and slotvalues (Raux et al., 2005; Chen et al., 2013) and the goal is to obtain a dialog policy that chooses”
ChartDialogs: Plotting from Natural Language Instructions (2020, background): “…and Polifroni, 2000; Bennett and Rudnicky, 2002; Asri et al., 2017; Budzianowski et al., 2018; Wei et al., 2018), restaurant (Hender-son et al., 2014; Bordes et al., 2017), bus (Raux et al., 2005; Williams et al., 2013), technical support (Lowe et al., 2015), and car agents (Eric et al., 2017).”
What is left to be understood in ATIS? (2010, methodology): “Another effort is the Let’s Go dialog system used by real users of the Pittsburgh bus transportation system [24].”
Incorporating Unstructured Textual Knowledge Sources into Neural Dialogue Systems (2015, background): “Using external information is of great importance to dialogue systems, particularly in the task-oriented setting (for example, helping users find movies or catch their bus using corresponding schedules [14, 10]).”