Feasibility Studies for Programming in Natural Language

Lieberman, Henry; Liu, Hugo

doi:10.1007/1-4020-5386-x_20

Cited by 24 publications

(14 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The non-programmers found that Metafor reduced their programming task time by 22%, while for intermediate programmers the figure was 11%. This result supports the initial intuition from [5] and [8] that natural language programming can be a useful tool, in particular for non-expert programmers.…”

Section: Set-based Dynamic Referencesupporting

confidence: 83%

“…In a similar vein, Lieberman & Liu [5] have conducted a feasibility study and showed how a partial understanding of a text, coupled with a dialogue with the user, can help non-expert users make their intentions more precise when designing a computer program. Their study resulted in a system called METAFOR [6], [7], able to translate natural language statements into class descriptions with the associated objects and methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

NLP (Natural Language Processing) for NLP (Natural Language Programming)

Mihalcea

Liu

Lieberman

2006

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Natural Language Processing holds great promise for making computer interfaces that are easier to use for people, since people will (hopefully) be able to talk to the computer in their own language, rather than learn a specialized language of computer commands. For programming, however, the necessity of a formal programming language for communicating with a computer has always been taken for granted. We would like to challenge this assumption. We believe that modern Natural Language Processing techniques can make possible the use of natural language to (at least partially) express programming ideas, thus drastically increasing the accessibility of programming to non-expert users. To demonstrate the feasibility of Natural Language Programming, this paper tackles what are perceived to be some of the hardest cases: steps and loops. We look at a corpus of English descriptions used as programming assignments, and develop some techniques for mapping linguistic constructs onto program structures, which we refer to as programmatic semantics.

show abstract

Section: Set-based Dynamic Referencesupporting

confidence: 83%

Section: Introductionmentioning

confidence: 99%

NLP (Natural Language Processing) for NLP (Natural Language Programming)

Mihalcea

Liu

Lieberman

2006

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…These represent a refinement and elaboration over earlier notions presented in (Liu & Lieberman, 2004b;Lieberman & Liu, 2004a). The theoretical conclusions enounced here are grounded in part in our analysis of the user study data of Pane, Ratanamahatana & Myers (2001) on non-programmers' solutions to programming problems like Pacman, which they were kind enough to share with us, and also in part in our practical experience with three generations of iterative design and reimplementation of the Metafor story-to-code interpreter.…”

Section: Principles Of Programmatic Semanticssupporting

confidence: 52%

Programmatic semantics for natural language interfaces

Liu¹,

Lieberman²

2005

CHI '05 Extended Abstracts on Human Factors in Computing Systems

Self Cite

View full text Add to dashboard Cite

An important way of making interfaces usable by nonexpert users is to enable the use of natural language input, as in natural language query interfaces to databases, or MUDs and MOOs. When the subject matter is about procedures, however, we have discovered that interfaces can take advantage of what we call Programmatic Semantics, procedural relations that can be inferred from the linguistic structure. Roughly, nouns can be interpreted as data structures; verbs are functions; adjectives are properties. Some linguistic forms imply conditionals, loops, and recursive structures.We illustrate the principles of Programmatic Semantics with a description of Metafor, a "brainstorming" editor for programs, analogous to an outlining tool for prose writing. Metafor interactively converts English sentences to partially specified program code, to be used as "scaffolding" for a more detailed program. A user study showed that Metafor is capable of capturing enough Programmatic Semantics to facilitate non-programming users and beginners' conceptualization of programming problems.

show abstract

“…Lieberman's work on Common Sense Reasoning (Lieberman et al, 2004) provides some evidence by using high-level knowledge bases to carry out automatic reasoning. In that work, mostly related to natural language-based interaction, the system tries to infer meaningful user definitions by using natural language (Lieberman and Liu, 2006). The authors assume that syntactical definitions are vague and imprecise, and so they need to be disambiguated using a semantic layer in the form of an ontology to obtain high-level information.…”

Section: Related Workmentioning

confidence: 99%