Towards Improving Predictive AAC using Crowdsourced Dialogues and Partner Context
The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Augmentative and Alternative Communication (AAC) devices typically rely on a language model to help make predictions or disambiguate user input. We investigate how to improve predictions in two-sided conversational dialogues. We collect and share a new corpus of crowdsourced everyday dialogues. We show how language models based on recurrent neural networks outperform N-gram models on these dialogues. We demonstrate further gains are possible using text obtained from an AAC user's communication partner, even when that text is partial or contains errors.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Using general dialogue data, some studies have shown substantial improvements in word prediction when language models consider the partner's speech in their prediction [31, 36].”
From “The less I type, the better”: How AI Language Models can Enhance or Impede Communication for AAC Users (2023) · cites this paper as [36]
Citations
Cites
Recurrent neural network based language model
Mikolov, T., Karafiát, M., Burget, L., Černocký, J., & Khudanpur, S. (2010) · Interspeech 2010 · doi:10.21437/interspeech.2010-343 · Cited by 5,390 · cited 1×
“We show how crowd workers can easily generate everyday conversational dialogues and how recurrent neural network language models (RNNLMs) [4] improve modeling of these crowdsourced dialogues.”
BackgroundIntelligent Selection of Language Model Training Data
Moore, R. C., & Lewis, W. D. (2010) · Cited by 702
Danescu-Niculescu-Mizil, C., & Lee, L. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1106.3077 · Cited by 312 · cited 1×
“Due to our relatively small crowdsourced corpus, we instead used dialogues from movies [1].”
MethodWisenburn, B., & Higginbotham, D. J. (2008) · Augmentative and Alternative Communication · doi:10.1080/07434610701740448 · Cited by 80 · cited 1×
“Speech context was used in the Converser AAC interface which recognized noun phrases from the speaking person and incorporated them into utterance templates [7].”
MethodVertanen, K., & Kristensson, P. O. (2011) · Cambridge University Engineering Department Publications Database · Cited by 80
Self-citationKane, S. K., Morris, M. R., Paradiso, A., & Campbell, J. (2017) · Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing · doi:10.1145/2998181.2998284 · Cited by 50 · cited 1×
“Communicating with an AAC device poses many chal lenges such as generating text sufficiently fast to take part in conversations, controlling the delivery of pre-entered text, conversation turn-taking, and expressing emotion [3].”
BackgroundFiannaca, A., Paradiso, A., Shah, M., & Morris, M. R. (2017) · Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing · doi:10.1145/2998181.2998215 · Cited by 49 · cited 1×
“Alternatively, a partner could explicitly suggest relevant words via a mobile app as in the AACrobat pro totype [2].”
Method
Research works printed but not linked: 4
- Danescu-Niculescu-Mizil C., 2011, Proc. CMCL
- Mikolov T., 2010, Proc. Interspeech
- Moore R. C., 2010, Proc. ACL
- Vertanen K., 2011, Proc. EMNLP
Cited by
Valencia, S., Cave, R., Kallarackal, K., Seaver, K., Terry, M., & Kane, S. K. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581560 · Cited by 97
“Using general dialogue data, some studies have shown substantial improvements in word prediction when language models consider the partner’s speech in their prediction [31, 36].”
BackgroundUsing large language models to accelerate communication for eye gaze typing users with ALS
Cai, S., Venugopalan, S., Seaver, K., Xiao, X., Tomanek, K., Jalasutram, S., Morris, M. R., Kane, S. K., Narayanan, A., MacDonald, R. L., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-53873-3 · Cited by 55
Fontana De Vargas, M., Yu, C., Shane, H. C., & Moffatt, K. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642080 · Cited by 30
“By using users personal information, such as the nature of their disability, age, literacy level, or user’s environment data, such as current location, time, or conversation partner’s messages [21, 45, 53], researchers have demonstrated key-stroke rate gains up to 71%.”
BackgroundA Survey of Technologies Facilitating Home and Community-Based Stroke Rehabilitation
Sun, X., Ding, J., Dong, Y., Ma, X., Wang, R., Jin, K., Zhang, H., & Zhang, Y. (2022) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2022.2050545 · Cited by 26
“Further more, multi-modal technologies are applied to capture more complex contextual data (Obiorah et al., 2017; Vargas, 2020; Vertanen, 2017).”
MethodContext-Aware Abbreviation Expansion Using Large Language Models
Cai, S., Venugopalan, S., Tomanek, K., Narayanan, A., Morris, M. R., & Brenner, M. P. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.91 · Cited by 39
Metadata
- Authors
- Vertanen, K.
- Affiliations
- Michigan Technological University (US)
- Corresponding author
- Vertanen, Keith
- ORCID
- Vertanen, Keith
- Venue
- Proceedings of the 19th International ACM SIGACCESS Conference on Computers and Accessibility
- Publisher
- ACM
- Published
- 2017-10-19
- Pages
- 347-348
- OpenAlex
- W2766018131
- Cited by
- 10
- References
- 7
- Citations by year
- 2025: 1 · 2024: 2 · 2023: 1 · 2022: 4 · 2019: 2
- FWCI
- 1.50
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) (publishedVersion)
- Digital Commons - Michigan Tech (Michigan Technological University) (submittedVersion)
- Topics
- Health Sciences › Health Professions › Occupational Therapy › Assistive Technology in Communication and Mobility
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Keywords
- augmentative and alternative communication, conversational dialogue, language models, recurrent neural networks, n-gram language models
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Towards Improving Predictive AAC using Crowdsourced Dialogues and Partner Context. https://app.cochat.ai/papers/10.1145/3132525.3134814
- The paper
- Vertanen, K. (2017). Towards Improving Predictive AAC using Crowdsourced Dialogues and Partner Context. Proceedings of the 19th International ACM SIGACCESS Conference on Computers and Accessibility. https://doi.org/10.1145/3132525.3134814
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.