Data-Driven Dialogue Systems for Social Agents

Bowden, Kevin K.; Oraby, Shereen; Misra, Amita; Wu, Jiaqi; Lukin, Stephanie M.; Walker, Marilyn A.

doi:10.1007/978-3-319-92108-2_6

Cited by 16 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1 lists the statistics of the dataset in its two versions. (1) The streaming version was tailored for streaming scenarios and included labels for all blocks mentioned in Section 4.1. Hence, the number of non-BC blocks substantially exceeded that of the blocks with BCs.…”

Section: Data Statisticsmentioning

confidence: 99%

Joint streaming model for backchannel prediction and automatic speech recognition

Choi,

Bang,

Kim

2024

ETRI Journal

View full text Add to dashboard Cite

In human conversations, listeners often utilize brief backchannels such as “uh‐huh” or “yeah.” Timely backchannels are crucial to understanding and increasing trust among conversational partners. In human–machine conversation systems, users can engage in natural conversations when a conversational agent generates backchannels like a human listener. We propose a method that simultaneously predicts backchannels and recognizes speech in real time. We use a streaming transformer and adopt multitask learning for concurrent backchannel prediction and speech recognition. The experimental results demonstrate the superior performance of our method compared with previous works while maintaining a similar single‐task speech recognition performance. Owing to the extremely imbalanced training data distribution, the single‐task backchannel prediction model fails to predict any of the backchannel categories, and the proposed multitask approach substantially enhances the backchannel prediction performance. Notably, in the streaming prediction scenario, the performance of backchannel prediction improves by up to 18.7% compared with existing methods.

show abstract

Section: Data Statisticsmentioning

confidence: 99%

Joint streaming model for backchannel prediction and automatic speech recognition

Choi,

Bang,

Kim

2024

ETRI Journal

View full text Add to dashboard Cite

show abstract

“…Other work that is focused on open-domain personalization has been focused on short exchanges [44], or used Twitter and TV Script data as a source of utterances [27]. This is not adequate for Alexa Prize conversations [5].…”

Section: Related Workmentioning

confidence: 99%

Let's Get Personal: Personal Questions Improve SocialBot Performance in the Alexa Prize

Bowden¹,

Walker²

2023

Preprint

View full text Add to dashboard Cite

There has been an increased focus on creating conversational opendomain dialogue systems in the spoken dialogue community. Unlike traditional dialogue systems, these conversational systems cannot assume any specific information need or domain restrictions, i.e., the only inherent goal is to converse with the user on an unknown set of topics. While massive improvements in Natural Language Understanding (NLU) and the growth of available knowledge resources can partially support a robust conversation, these conversations generally lack the rapport between two humans that know each other. We developed a robust open-domain conversational system, Athena, that real Amazon Echo users access and evaluate at scale in the context of the Alexa Prize competition. We experiment with methods intended to increase intimacy between Athena and the user by heuristically developing a rule-based user model that personalizes both the current and subsequent conversations and evaluating specific personal opinion question strategies in A/B studies. Our results show a statistically significant positive impact on perceived conversation quality and length when employing these strategies.

show abstract

“…Teams experimented with approaches to track context and dialogue states, and corresponding transitions to maintain dialogue flow. For example, Alquist and Slugbot (Bowden et al 2017) 4 modeled dialogue flow as a state graph. These and other techniques helped socialbots produce coherent responses in an ongoing multiturn conversation and guided the direction of the conversation as needed.…”

Section: Addressing Problems In Creating Conversational Agentsmentioning

confidence: 99%

Alexa Prize — State of the Art in Conversational AI

et al. 2018

View full text Add to dashboard Cite

To advance the state of the art in conversational AI, Amazon launched the Alexa Prize, a 2.5 million dollar competition that challenges university teams to build conversational agents, or "socialbots", that can converse coherently and engagingly with humans on popular topics for 20 minutes. The Alexa Prize offers the academic community a unique opportunity to perform research at scale with real conversational data obtained by interacting with millions of Alexa users, along with user-provided ratings and feedback, over several months. This enables teams to effectively iterate, improve and evaluate their socialbots throughout the competition. Sixteen teams were selected for the inaugural competition last year. To build their socialbots, the students combined state-of-the-art techniques with their own novel strategies in the areas of Natural Language Understanding and Conversational AI. This article reports on the research conducted over the 2017-2018 year. While the 20 minute grand challenge was not achieved in the first year, the competition produced several conversational agents that advanced the state of the art, are interesting for everyday users to interact with, and help form a baseline for the second year of the competition.

show abstract

Data-Driven Dialogue Systems for Social Agents

Cited by 16 publications

References 18 publications

Joint streaming model for backchannel prediction and automatic speech recognition

Joint streaming model for backchannel prediction and automatic speech recognition

Let's Get Personal: Personal Questions Improve SocialBot Performance in the Alexa Prize

Alexa Prize — State of the Art in Conversational AI

Contact Info

Product

Resources

About