Can I finish?: learning when to respond to incremental interpretation results in interactive dialogue
Open accessThe DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
We investigate novel approaches to responsive overlap behaviors in dialogue systems, opening possibilities for systems to interrupt, acknowledge or complete a user's utterance while it is still in progress. Our specific contributions are a method for determining when a system has reached a point of maximal understanding of an ongoing user utterance, and a prototype implementation that shows how systems can use this ability to strategically initiate system completions of user utterances. More broadly, this framework facilitates the implementation of a range of overlap behaviors that are common in human dialogue, but have been largely absent in dialogue systems.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Referring as a collaborative process
Clark, H. H., & Wilkes-Gibbs, D. (1986) · Cognition · doi:10.1016/0010-0277(86)90010-7 · Cited by 2,401 · cited 2×
“(1996)), performing collaborative completions (Clark and Wilkes-Gibbs, 1986), or some corrections, it is important not only to predict the meaning, but also the form of the remaining part of the utterance.”
BackgroundOn the semantics and pragmatics of linguistic feedback
ALLWOOD, J., NIVRE, J., & AHLSÉN, E. (1992) · Journal of Semantics · doi:10.1093/jos/9.1.1 · Cited by 442 · cited 1×
“It also enables giving early feedback (e.g., head nods and shakes, facial expressions, gaze shifts, and verbal backchannels) to signal how well things are being perceived, understood, and evaluated (Allwood et al., 1992).”
Background
Cited by
Turn-taking in conversational systems and human-robot interaction: a review
Skantze, G. (2021) · Computer Speech & Language · doi:10.1016/j.csl.2020.101178 · Cited by 298
Safety First: Conversational Agents for Health Care
Bickmore, T., Trinh, H., Asadi, R., & Olafsson, S. (2018) · Human–Computer Interaction Series · doi:10.1007/978-3-319-95579-7_3 · Cited by 50
Challenges in Building Highly Interactive Dialogue Systems
Ward, N. G., & DeVault, D. (2016) · AI Magazine · doi:10.1609/aimag.v37i4.2687 · Cited by 46
“…analysis of other recent advances in spoken dialog systems, intelligent virtual agents, and human-robot interaction, including (Gratch et al. 2007; DeVault, Sagae, and Traum 2009; Bohus and Horvitz 2011; Forbes-Riley and Litman 2011; Acosta and Ward 2011; Raux and Eskenazi 2012; Andrist, Mutlu,…”
BackgroundSelf-citationA model for incremental grounding in spoken dialogue systems
Visser, T., Traum, D., DeVault, D., & op den Akker, R. (2014) · Journal on Multimodal User Interfaces · doi:10.1007/s12193-013-0147-7 · Cited by 18
Self-citationGrounding as a Collaborative Process
Benotti, L., & Blackburn, P. (2021) · Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume · doi:10.18653/v1/2021.eacl-main.41 · Cited by 14
“Schlangen and others have shown in detail how the ongoing exchange of these roles is so natural that we complete and correct each others sentences in incremental approaches to dialog (Schlangen and Skantze, 2009; DeVault et al., 2009; Baumann and Schlangen, 2012; DeVault and Traum, 2013; Kennington and Schlangen, 2017…”
Background
Metadata
- Authors
- DeVault, D., Sagae, K., & Traum, D.
- Venue
- Proceedings of the SIGDIAL 2009 Conference on The 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue - SIGDIAL '09
- Published
- 2009
- Pages
- 11-20
- OpenAlex
- W1986532700
- Cited by
- 70
- References
- 2
- FWCI
- 6.58
- Type
- conference paper
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.