A colorful approach to text processing by example

Yessenov, Kuat; Tulsiani, Shubham; Menon, Aditya Krishna; Miller, Robert C.; Gulwani, Sumit; Lampson, Butler; Kalai, Adam Tauman

doi:10.1145/2501988.2502040

Cited by 33 publications

(26 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The FlashProg UI builds over the STEPS approach [32] to PBE, wherein the user breaks down a sophisticated task into a sequence of simpler steps, and each step is automated using PBE. We conducted a user study, where we asked participants to extract structured data from semi-structured text files using FlashProg.…”

Section: Flashprog Framework For Data Manipulationmentioning

confidence: 99%

See 1 more Smart Citation

User Interaction Models for Disambiguation in Programming by Example

Mayer

Soares

Grechkin

et al. 2015

Proceedings of the 28th Annual ACM Symposium on User Interface Software &Amp; Technology

Self Cite

View full text Add to dashboard Cite

Programming by Examples (PBE) has the potential to revolutionize end-user programming by enabling end users, most of whom are non-programmers, to create small scripts for automating repetitive tasks. However, examples, though often easy to provide, are an ambiguous specification of the user's intent. Because of that, a key impedance in adoption of PBE systems is the lack of user confidence in the correctness of the program that was synthesized by the system. We present two novel user interaction models that communicate actionable information to the user to help resolve ambiguity in the examples. One of these models allows the user to effectively navigate between the huge set of programs that are consistent with the examples provided by the user. The other model uses active learning to ask directed example-based questions to the user on the test input data over which the user intends to run the synthesized program. Our user studies show that each of these models significantly reduces the number of errors in the performed task without any difference in completion time. Moreover, both models are perceived as useful, and the proactive active-learning based model has a slightly higher preference regarding the users' confidence in the result.

show abstract

Section: Flashprog Framework For Data Manipulationmentioning

confidence: 99%

“…FlashProg user interface is inspired by that of the STEPS system [32] that uses hierarchical structure coloring for text extraction and manipulation. STEPS showed the usefulness of PBE systems for text processing: STEPS users completed more tasks and were faster than conventional programmers.…”

Section: Related Workmentioning

confidence: 99%

User Interaction Models for Disambiguation in Programming by Example

Mayer

Soares

Grechkin

et al. 2015

Proceedings of the 28th Annual ACM Symposium on User Interface Software &Amp; Technology

Self Cite

View full text Add to dashboard Cite

show abstract

“…al. [40] present a programming by steps system, where the user provides mock examples at each step. Our steps programming model allows use of both natural language and examples, but more significantly, its support for emphasis, highlighting, and implicit referencing allows easy communication between various steps.…”

Section: Related Workmentioning

confidence: 99%

“…These operations are not easily expressible using examples. In particular, filter operations would require too many examples, and reduce operations may require the user to construct small mock examples [40]. We studied Excel help forums and observed that end users often struggle with such tasks and communicate their intent to the forum experts using natural language.…”

Section: Introductionmentioning

confidence: 99%

NLyze

Gulwani

Marron

2014

Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data

Self Cite

View full text Add to dashboard Cite

Millions of computer end users need to perform tasks over tabular spreadsheet data, yet lack the programming knowledge to do such tasks automatically. This paper describes the design and implementation of a robust natural language based interface to spreadsheet programming. Our methodology involves designing a typed domain-specific language (DSL) that supports an expressive algebra of map, filter, reduce, join, and formatting capabilities at a level of abstraction appropriate for non-expert users. The key algorithmic component of our methodology is a translation algorithm for converting a natural language specification in the context of a given spreadsheet to a ranked set of likely programs in the DSL. The translation algorithm leverages the spreadsheet spatial and temporal context to assign interpretations to specifications with implicit references, and is thus robust to a variety of ways in which end users can express the same task. The translation algorithm builds over ideas from keyword programming and semantic parsing to achieve both high precision and high recall. We implemented the system as an Excel add-in called NLyze that supports a rich user interaction model including annotating the user's natural language specification and explaining the synthesized DSL programs by paraphrasing them into structured English. We collected a total of 3570 English descriptions for 40 spreadsheet tasks and our system was able to generate the intended interpretation as the top candidate for 94% (97% for the top 3) of those instances.

show abstract

“…Below in text classification in information retrieval and analysis of emotional huge role [11][12], for example.…”

Section: Introductionmentioning

confidence: 99%