Live Programming By Example

Santolucito, Mark; Hallahan, William T.; Piskač, Ružica

doi:10.1145/3290607.3313266

Cited by 12 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…WebRobot adopts a human-in-theloop interaction model which has shown to be an effective way to incorporate human inputs when training AI systems in the HCI community [19,45]. This model has been used in the context of program synthesis, mostly interactive PBE [23,41,43,51,60,65]. In contrast, our work incorporates human inputs in PBD and proposes a new human-in-the-loop model.…”

Section: Related Workmentioning

confidence: 99%

WebRobot: Web Robotic Process Automation using Interactive Programming-by-Demonstration

Dong¹,

Huang²,

Lam³

et al. 2022

Preprint

View full text Add to dashboard Cite

It is imperative to democratize robotic process automation (RPA), as RPA has become a main driver of the digital transformation but is still technically very demanding to construct, especially for non-experts. In this paper, we study how to automate an important class of RPA tasks, dubbed web RPA, which are concerned with constructing software bots that automate interactions across data and a web browser. Our main contributions are twofold. First, we develop a formal foundation which allows semantically reasoning about web RPA programs and formulate its synthesis problem in a principled manner. Second, we propose a web RPA program synthesis algorithm based on a new idea called speculative rewriting. This leads to a novel speculate-and-validate methodology in the context of rewrite-based program synthesis, which has also shown to be both theoretically simple and practically efficient for synthesizing programs from demonstrations. We have built these ideas in a new interactive synthesizer called WebRobot and evaluate it on 76 web RPA benchmarks. Our results show that WebRobot automated a majority of them effectively. Furthermore, we show that WebRobot compares favorably with a conventional rewrite-based synthesis baseline implemented using egg. Finally, we conduct a small user study demonstrating WebRobot is also usable. CCS Concepts:• Software and its engineering → Automatic programming.

show abstract

Section: Related Workmentioning

confidence: 99%

WebRobot: Web Robotic Process Automation using Interactive Programming-by-Demonstration

Dong¹,

Huang²,

Lam³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…also ranked and inferred automatically from the user's input. In Santolucito et al (2019) the authors use CVC4's Syntaxguided synthesis (SyGuS) algorithm (Reynolds and Tinelli 2017) for Javascript live coding.The most related work in this area is TaCLe (Paramonov et al 2017;Kolb et al 2017). TaCLe reconstructs the formulae used in a data spreadsheet based on a comma-separated file.…”

Section: Related Workmentioning

confidence: 99%

AUTOMAT[R]IX: learning simple matrix pipelines

2021

View full text Add to dashboard Cite

Matrices are a very common way of representing and working with data in data science and artificial intelligence. Writing a small snippet of code to make a simple matrix transformation is frequently frustrating, especially for those people without an extensive programming expertise. We present AUTOMATIX, a system that is able to induce R program snippets from a single (and possibly partial) matrix transformation example provided by the user. Our learning algorithm is able to induce the correct matrix pipeline snippet by composing primitives from a library. Because of the intractable search space—exponential on the size of the library and the number of primitives to be combined in the snippet, we speed up the process with (1) a typed system that excludes all combinations of primitives with inconsistent mapping between input and output matrix dimensions, and (2) a probabilistic model to estimate the probability of each sequence of primitives from their frequency of use and a text hint provided by the user. We validate AUTOMATIX with a set of real programming queries involving matrices from Stack Overflow, showing that we can learn the transformations efficiently, from just one partial example.

show abstract

“…Live programming [57] helps novice programmers to understand their codes, where they can manipulate the input by directly editing the codes and manipulate the output by providing examples of the desired output. Beyond computational tasks, PBE tools also support creative tasks such as music creation by example [20], where a software takes a song as an example and allows the user to interactively mix the AI-generated music.…”

Section: Programming-by-example (Pbe) Approachesmentioning

confidence: 99%

“…Example-based interactions have been explored as a method to bridge the usability gap of computational systems that typically require precise programs from users, such as in our user scenario above. Under the programming by example (PBE) paradigm (also known as programming by demonstration), instead of writing a precise program to specify their intent, users only need to provide a few examples of the mechanism or result they desire [7,24,43,56]. Prior work conducted user studies to contrast PBE tools against traditional alternatives [11,41,47,55].…”

mentioning

confidence: 99%

Example-Driven User Intent Discovery: Empowering Users to Cross the SQL Barrier Through Query by Example

Fariha¹,

Cousins²,

Mahyar³

et al. 2020

Preprint

View full text Add to dashboard Cite

Traditional data systems require specialized technical skills where users need to understand the data organization and write precise queries to access data. Therefore, novice users who lack technical expertise face hurdles in perusing and analyzing data. Existing tools assist in formulating queries through keyword search, query recommendation, and query auto-completion, but still require some technical expertise. An alternative method for accessing data is Query by Example (QBE), where users express their data exploration intent simply by providing examples of their intended data. We study a state-of-the-art QBE system called SQUID, and contrast it with traditional SQL querying. Our comparative user studies demonstrate that users with varying expertise are significantly more effective and efficient with SQUID than SQL. We find that SQUID eliminates the barriers in studying the database schema, formalizing task semantics, and writing syntactically correct SQL queries, and thus, substantially alleviates the need for technical expertise in data exploration.

show abstract

Live Programming By Example

Cited by 12 publications

References 12 publications

WebRobot: Web Robotic Process Automation using Interactive Programming-by-Demonstration

WebRobot: Web Robotic Process Automation using Interactive Programming-by-Demonstration

AUTOMAT[R]IX: learning simple matrix pipelines

Example-Driven User Intent Discovery: Empowering Users to Cross the SQL Barrier Through Query by Example

Contact Info

Product

Resources

About