Achieving Common Ground in Multi-modal Dialogue

Alikhani, Malihe; Stone, Matthew

doi:10.18653/v1/2020.acl-tutorials.3

Cited by 2 publications

(2 citation statements)

References 57 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…People adapt by initially estimating the common ground they share with a particular partner, by monitoring the positive and negative evidences of understanding (aka grounding acts) and by adapting their initial common ground estimate accordingly. Alikhani and Stone (2020) explain that dialog systems can participate in collaborative grounding by ensuring they get attention and feedback from their users and tracking user state. Such pragmatic mechanisms have been explored, including those for dealing with problems related to joint attention (Koller et al, 2012;Koleva et al, 2015;Tan et al, 2020), engagement (Bohus and Horvitz, 2014;Foster et al, 2017), turn taking and incremental interpretation (Schlangen and Skantze, 2009;Selfridge et al, 2012;DeVault and Traum, 2013;Eshghi et al, 2015) corrections and clarifications (Villalba et al, 2017;Ginzburg and Fernández, 2010) and dialog management (DeVault and Stone, 2009;Selfridge et al, 2012).…”

Section: Collaborative Grounding: Basic Mechanismsmentioning

confidence: 99%

Grounding as a Collaborative Process

Benotti¹,

Blackburn

2021

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

View full text Add to dashboard Cite

Collaborative grounding is a fundamental aspect of human-human dialog which allows people to negotiate meaning. In this paper we argue that it is missing from current deep learning approaches to dialog and interactive systems. Our central point is that making mistakes and being able to recover from them collaboratively is a key ingredient in grounding meaning. We illustrate the pitfalls of being unable to ground collaboratively, discuss what can be learned from the language acquisition and dialog systems literature, and reflect on how to move forward.

show abstract

Section: Collaborative Grounding: Basic Mechanismsmentioning

confidence: 99%

Grounding as a Collaborative Process

Benotti¹,

Blackburn

2021

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

View full text Add to dashboard Cite

show abstract

“…Collaborative grounding, on the other hand, deals with the dynamics of conversation (the ongoing exchange of speaker and hearer roles) and is rooted in situationally relevant aspects of socioperception. Alikhani and Stone (2020) note several basic mechanisms that contribute to collaborative grounding, including those for dealing with joint attention (Koller et al, 2012;Koleva et al, 2015;Tan et al, 2020), engagement (Bohus and Horvitz, 2014;Foster et al, 2017), turn taking and incremental interpretation (Schlangen and Skantze, 2009;Selfridge et al, 2012;DeVault and Traum, 2013;Eshghi et al, 2015) corrections and clarifications (Villalba et al, 2017;Ginzburg and Fernández, 2010) and dialogue management (DeVault and Stone, 2009;Selfridge et al, 2012). These mechanisms have been studied for different kinds of applications (Denis, 2010;Dzikovska et al, 2010Dzikovska et al, , 2012.…”

Section: Collaborative and Perceptual Groundingmentioning

confidence: 99%

A recipe for annotating grounded clarifications

Benotti

Blackburn

2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

In order to interpret the communicative intents of an utterance, it needs to be grounded in something that is outside of language; that is, grounded in world modalities. In this paper we argue that dialogue clarification mechanisms make explicit the process of interpreting the communicative intents of the speaker's utterances by grounding them in the various modalities in which the dialogue is situated. This paper frames dialogue clarification mechanisms as an understudied research problem and a key missing piece in the giant jigsaw puzzle of natural language understanding. We discuss both the theoretical background and practical challenges posed by this problem, and propose a recipe for obtaining grounding annotations. We conclude by highlighting ethical issues that need to be addressed in future work. 1 We are suspicious of the common assumption that requests for information regarding references that are grounded in vision (e.g. the red or the blue jacket?) are clarifications, whereas requests for information grounded in other modalities are not (e.g. do I take the stairs up or down?).2 See also the supplement on ethical considerations.

show abstract

Achieving Common Ground in Multi-modal Dialogue

Cited by 2 publications

References 57 publications

Grounding as a Collaborative Process

Grounding as a Collaborative Process

A recipe for annotating grounded clarifications

Contact Info

Product

Resources

About