PUMICE: A Multi-Modal Agent that Learns Concepts and Conditionals from Natural Language and Demonstrations
The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Natural language programming is a promising approach to enable end users to instruct new tasks for intelligent agents. However, our formative study found that end users would often use unclear, ambiguous or vague concepts when naturally instructing tasks in natural language, especially when specifying conditionals. Existing systems have limited support for letting the user teach agents new concepts or explaining unclear concepts. In this paper, we describe a new multi-modal domain-independent approach that combines natural language programming and programming-by-demonstration to allow users to first naturally describe tasks and associated conditions at a high level, and then collaborate with the agent to recursively resolve any ambiguities or vagueness through conversations and demonstrations. Users can also define new procedures and concepts by demonstrating and referring to contents within GUIs of existing mobile apps. We demonstrate this approach in PUMICE, an end-user programmable agent that implements this approach. A lab study with 10 users showed its usability.
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
Wing, J. M. (2006) · Communications of the ACM · doi:10.1145/1118178.1118215 · Cited by 8,102
Freebase: a collaboratively created graph database for structuring human knowledge
Bollacker, K., Evans, C., Paritosh, P., Sturge, T., & Taylor, J. (2008) · Proceedings of the 2008 ACM SIGMOD international conference on Management of data · doi:10.1145/1376616.1376746 · Cited by 4,852
A survey of robot learning from demonstration
Argall, B. D., Chernova, S., Veloso, M., & Browning, B. (2009) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2008.10.024 · Cited by 3,227
A Syntactic Neural Model for General-Purpose Code Generation
Yin, P., & Neubig, G. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1041 · Cited by 623
A Syntactic Neural Model for General-Purpose Code Generation
Yin, P., & Neubig, G. (2017) · arXiv · doi:10.48550/arxiv.1704.01696 · Cited by 585
Sikuli: using GUI screenshots for search and automation
Yeh, T., Chang, T.-H., & Miller, R. C. (2009) · Proceedings of the 22nd annual ACM symposium on User interface software and technology · doi:10.1145/1622176.1622213 · Cited by 346 · cited 2×
“Sikuli [50] allows users to create conditionals in a scripting language, which is not suitable for end users without programming expertise.”
BackgroundMethodLearning to mine aligned code and natural language pairs from stack overflow
Yin, P., Deng, B., Chen, E., Vasilescu, B., & Neubig, G. (2018) · Proceedings of the 15th International Conference on Mining Software Repositories · doi:10.1145/3196398.3196408 · Cited by 218 · cited 1×
“This approach also provides more interpretable results and requires less training data than neural network approaches (e.g., [51, 52]).”
BackgroundProgrammers Are Users Too: Human-Centered Methods for Improving Programming Tools
Myers, B. A., Ko, A. J., LaToza, T. D., & Yoon, Y. (2016) · Computer · doi:10.1109/mc.2016.200 · Cited by 144
Self-citationInstructable Intelligent Personal Agent
Azaria, A., Krishnamurthy, J., & Mitchell, T. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10357 · Cited by 70
Self-citationInteraction Proxies for Runtime Repair and Enhancement of Mobile Application Accessibility
Zhang, X., Ross, A. S., Caspi, A., Fogarty, J., & Wobbrock, J. O. (2017) · Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025846 · Cited by 59 · cited 1×
“P UMICE uses an interaction proxy overlay [53] for recording, so that it can record all values visible on the screen, not limited to the selectable or clickable ones.”
Research works printed but not linked: 44
- James Allen, Nathanael Chambers, George Ferguson, Lucian Galescu, Hyuckchul Jung, Mary Swift, and William Taysom. 2007. PLOW: A Collaborative Task Learning Agent. In Proceedings of the 22Nd National Conference on Artificial Intelligence - Volume 2 (AAAI'07). AAAI Press, Vancouver, British Columbia, Canada, 1514--1519.
- Bruce W. Ballard and Alan W. Biermann. 1979. Programming in Natural Language “NLC” As a Prototype. In Proceedings of the 1979 Annual Conference (ACM '79). ACM, New York, NY, USA, 228--237. http://dx.doi.org/10.1145/800177.810072 · DOI
- 10.18653/v1/D13-1160 · DOI · Paper page
- Alan W. Biermann. 1983. Natural Language Programming. In Computer Program Synthesis Methodologies (NATO Advanced Study Institutes Series), Alan W. Biermann and Gerard Guiho (Eds.). Springer Netherlands, 335--368.
- 10.1145/3242587.3242661 · DOI · Paper page
- Jacob Cohen. 1960. A coefficient of agreement for nominal scales. Educational and psychological measurement 20, 1 (1960), 37--46.
- Allen Cypher and Daniel Conrad Halbert. 1993. Watch what I do: programming by demonstration. MIT press.
- 10.1145/3173574.3174047 · DOI · Paper page
- 10.1145/1576246.1531372 · DOI
- 10.1006/jvlc.1996.0009 · DOI · Paper page
- H Paul Grice, Peter Cole, Jerry Morgan, and others. 1975. Logic and conversation. 1975 (1975), 41--58.
- Björn Hartmann, Leslie Wu, Kevin Collins, and Scott R. Klemmer. 2007. Programming by a Sample: Rapidly Creating Web Applications with D.Mix. In Proceedings of the 20th Annual ACM Symposium on User Interface Software and Technology (UIST '07). ACM, New York, NY, USA, 241--250. http://dx.doi.org/10.1145/1294211.1294254 · DOI · Paper page
- 10.1145/3234508 · DOI
- Rohit J. Kate, Yuk Wah Wong, and Raymond J. Mooney. 2005. Learning to Transform Natural to Formal Languages. In Proceedings of the 20th National Conference on Artificial Intelligence - Volume 3 (AAAI'05). AAAI Press, Pittsburgh, Pennsylvania, 1062--1068. http://dl.acm.org/citation.cfm?id=1619499.1619504
- Tessa Lau, Steven A. Wolfman, Pedro Domingos, and Daniel S. Weld. 2001. Your Wish is My Command. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, Chapter Learning Repetitive Text-editing Procedures with SMARTedit, 209--226. http://dl.acm.org/citation.cfm?id=369505.369519
- 10.1145/1357054.1357323 · DOI · Paper page
- Toby Jia-Jun Li, Amos Azaria, and Brad A. Myers. 2017. SUGILITE: Creating Multimodal Smartphone Automation by Demonstration. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems (CHI '17). ACM, New York, NY, USA, 6038--6049. http://dx.doi.org/10.1145/3025453.3025483 · DOI · Paper page
- Toby Jia-Jun Li, Igor Labutov, Xiaohan Nancy Li, Xiaoyi Zhang, Wenze Shi, Tom M. Mitchell, and Brad A. Myers. 2018. APPINITE: A Multi-Modal Interface for Specifying Data Descriptions in Programming by Demonstration Using Verbal Instructions. In Proceedings of the 2018 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC 2018).
- Toby Jia-Jun Li, Yuanchun Li, Fanglin Chen, and Brad A. Myers. 2017. Programming IoT Devices by Demonstration Using Mobile Apps. In End-User Development, Simone Barbosa, Panos Markopoulos, Fabio Paterno, Simone Stumpf, and Stefano Valtolina (Eds.). Springer International Publishing, Cham, 3--17.
- Toby Jia-Jun Li and Oriana Riva. 2018. KITE: Building conversational bots from mobile apps. In Proceedings of the 16th ACM International Conference on Mobile Systems, Applications, and Services (MobiSys 2018). ACM.
- Henry Lieberman. 2001. Your wish is my command: Programming by example. Morgan Kaufmann.
- Henry Lieberman and Hugo Liu. 2006. Feasibility studies for programming in natural language. In End User Development. Springer, 459--473.
- 10.1609/aimag.v25i4.1785 · DOI
- 10.1147/sj.353.0539 · doi:10.1147/sj.353.0539
- James Lin, Jeffrey Wong, Jeffrey Nichols, Allen Cypher, and Tessa A. Lau. 2009. End-user Programming of Mashups with Vegemite. In Proceedings of the 14th International Conference on Intelligent User Interfaces (IUI '09). ACM, New York, NY, USA, 97--106. http://dx.doi.org/10.1145/1502650.1502667 · DOI · Paper page
- 10.1023/B:BTTJ.0000047600.45421.6d · DOI · Paper page
- Christopher J. MacLellan, Erik Harpstead, Robert P. Marinier III, and Kenneth R. Koedinger. 2018. A Framework for Natural Cognitive System Training Interactions . Advances in Cognitive Systems (2018).
- 10.1145/176789.176792 · DOI · Paper page
- 10.1016/S0097-8493(00)00085-6 · DOI
- 10.3115/v1/P14-5010 · DOI · Paper page
- Rada Mihalcea, Hugo Liu, and Henry Lieberman. 2006. NLP (Natural Language Processing) for NLP (Natural Language Programming). In Computational Linguistics and Intelligent Text Processing (Lecture Notes in Computer Science), Alexander Gelbukh (Ed.). Springer Berlin Heidelberg, 319--330.
- 10.1145/3191513 · DOI · Paper page
- 10.1007/978--3--319--60291--2_1 · doi:10.1007/978--3--319--60291--2_1
- 10.1145/1015864.1015888 · DOI · Paper page
- 10.1145/302979.303163 · DOI · Paper page
- 10.1145/319382.319398 · DOI · Paper page
- 10.1006/ijhc.2000.0410 · DOI · Paper page
- 10.3115/v1/P15-1142 · DOI · Paper page
- Fabio Paterno and Volker Wulf. 2017. New Perspectives in End-User Development (1st ed.). Springer.
- 10.1145/325737.325845 · DOI · Paper page
- 10.1145/2641580.2641615 · DOI
- 10.18653/v1/D17-1161 · DOI
- Anselm Strauss and Juliet M. Corbin. 1990. Basics of qualitative research: Grounded theory procedures and techniques. Sage Publications, Inc.
- David Vadas and James R Curran. 2005. Programming with unrestricted natural language. In Proceedings of the Australasian Language Technology Workshop 2005. 191--199.
Cited by
Enabling Conversational Interaction with Mobile UI using Large Language Models
Wang, B., Li, G., & Li, Y. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580895 · Cited by 156
“When a conversational agent fails to understand or carry out the tasks associated with the user’s commands, prior work has leveraged programming by demonstration technique that asks users to provide tasks demonstrations to teach the agent [31, 35].”
BackgroundIn-IDE Code Generation from Natural Language: Promise and Challenges
Xu, F. F., Vasilescu, B., & Neubig, G. (2022) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3487569 · Cited by 154
Liu, M. X., Sarkar, A., Negreanu, C., Zorn, B., Williams, J., Toronto, N., & Gordon, A. D. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580817 · Cited by 119
Zhang, Z., Gao, J., Dhaliwal, R. S., & Li, T. J.-J. (2023) · Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586183.3606800 · Cited by 108
Self-citationExploring the Learnability of Program Synthesizers by Novice Programmers
Jayagopal, D., Lubin, J., & Chasins, S. E. (2022) · Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3526113.3545659 · Cited by 40
“Others focus exclusively on one novel synthesizer, with no control condition, and assess whether users can complete tasks with the tool at all [14, 41, 68].”
Background
Metadata
- Authors
- Li, T. J.-J., Radensky, M., Jia, J., Singarajah, K., Mitchell, T. M., & Myers, B. A.
- Venue
- Proceedings of the 32nd Annual ACM Symposium on User Interface Software and Technology
- Publisher
- ACM
- Published
- 2019-10-17
- Pages
- 577-589
- OpenAlex
- W2972018816
- Cited by
- 111
- References
- 10
- FWCI
- 3.27
- Type
- conference paper
- Language
- en
- Open access
- closed
- Funders
- National Science Foundation (IIS-1814472)
- J.P. Morgan
- Verizon
- Oath
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: PUMICE: A Multi-Modal Agent that Learns Concepts and Conditionals from Natural Language and Demonstrations. https://app.cochat.ai/papers/10.1145/3332165.3347899
- The paper
- Li, T. J.-J., Radensky, M., Jia, J., Singarajah, K., Mitchell, T. M., & Myers, B. A. (2019). PUMICE: A Multi-Modal Agent that Learns Concepts and Conditionals from Natural Language and Demonstrations. Proceedings of the 32nd Annual ACM Symposium on User Interface Software and Technology. https://doi.org/10.1145/3332165.3347899
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.