Where's the "party" in "multi-party"?

Aoki, Paul M.; Szymanski, Margaret H.; Plurkowski, Luke; Thornton, James D.; Woodruff, Allison; Yi, Weilie

doi:10.1145/1180875.1180934

Cited by 11 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, a number of remarkable and relevant systematic practices do exist for multi-party conversation, such as a preference for answers to questions to be provided by any member as opposed to the selected next speaker simply providing a response [44]. Work also details how the formation of multiple smaller conversations can take place (called "conversational floors" [1,10]), to allow for multiple members to talk at once non-problematically without requiring overlap resolution [41]. During our analysis we were sensitive to this although we do not frame our findings in these terms and instead we let the character of talk emerge as we explicate members' actions.…”

Section: Multi-party Conversationmentioning

confidence: 99%

"Do Animals Have Accents?"

Porcheron

Fischer

Sharples

2017

Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing

100

View full text Add to dashboard Cite

In this paper we unpack the use of conversational agents, or so-called intelligent personal assistants (IPAs), in multiparty conversation amongst a group of friends while they are socialising in a café. IPAs such as Siri or Google Now can be found on a large proportion of personal smartphones and tablets, and are promoted as 'natural language' interfaces. The question we pursue here is how they are actually drawn upon in conversational practice? In our work we examine the use of these IPAs in a mundane and commonplace setting and employ an ethnomethodological perspective to draw out the character of the IPA-use in conversation. Additionally, we highlight a number of nuanced practicalities of their use in multi-party settings. By providing a depiction of the nature and methodical practice of their use, we are able to contribute our findings to the design of IPAs.

show abstract

Section: Multi-party Conversationmentioning

confidence: 99%

"Do Animals Have Accents?"

Porcheron

Fischer

Sharples

2017

Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing

100

View full text Add to dashboard Cite

show abstract

“…For example, although an internet relay chat (IRC) has a single message stream, multiple participants might be simultaneously chatting on different topics. At a cocktail party, people organize several groups in the same physical space and chat with each other within each group ( Aoki et al., 2003 ; Aoki et al., 2006 ). An individual participant could be involved in all dialogue floors in such cases because the dialogue contents are freely visible to all participants.…”

Section: Introductionmentioning

confidence: 99%

End-to-end dialogue structure parsing on multi-floor dialogue based on multi-task learning

et al. 2023

View full text Add to dashboard Cite

A multi-floor dialogue consists of multiple sets of dialogue participants, each conversing within their own floor. In the multi-floor dialogue, at least one multi-communicating member who is a participant of multiple floors and coordinates each to achieve a shared dialogue goal. The structure of such dialogues can be complex, involving intentional structure and relations that are within or across floors. In this study, We proposed a neural dialogue structure parser with an attention mechanism that applies multi-task learning to automatically identify the dialogue structure of multi-floor dialogues in a collaborative robot navigation domain. Furthermore, we propose to use dialogue response prediction as an auxiliary objective of the multi-floor dialogue structure parser to enhance the consistency of the multi-floor dialogue structure parsing. Our experimental results show that our proposed model improved the dialogue structure parsing performance more than conventional models in multi-floor dialogue.

show abstract

“…Multi-party conversations generally involve three or more speakers in a single dialogue, in which the speaker utterances are interleaved, and multiple topics may be discussed concurrently (Aoki et al, 2006). This causes inconvenience for dialogue participant to digest the utterances and respond to a particular topic thread.…”

Section: Introductionmentioning

confidence: 99%

Conversation Disentanglement with Bi-Level Contrastive Learning

Huang¹,

Zhang²,

Fei³

et al. 2022

Findings of the Association for Computational Linguistics: EMNLP 2022

View full text Add to dashboard Cite

Conversation disentanglement aims to group utterances into detached sessions, which is a fundamental task in processing multi-party conversations. Existing methods have two main drawbacks. First, they overemphasize pairwise utterance relations but pay inadequate attention to the utterance-to-context relation modeling. Second, a huge amount of human annotated data is required for training, which is expensive to obtain in practice. To address these issues, we propose a general disentangle model based on bi-level contrastive learning. It brings closer utterances in the same session while encourages each utterance to be near its clustered session prototypes in the representation space. Unlike existing approaches, our disentangle model works in both supervised settings with labeled data and unsupervised settings when no such data is available. The proposed method achieves new state-of-the-art performance results on both settings across several public datasets.

show abstract

Where's the "party" in "multi-party"?

Cited by 11 publications

References 25 publications

"Do Animals Have Accents?"

"Do Animals Have Accents?"

End-to-end dialogue structure parsing on multi-floor dialogue based on multi-task learning

Conversation Disentanglement with Bi-Level Contrastive Learning

Contact Info

Product

Resources

About