Rada Mihalcea, Hugo Liu & Henry Lieberman (2006). NLP (natural language processing) for NLP (natural language programming). Computational Linguistics and Intelligent Text Processing (Ed. A. Gelbukh), LNCS 3878, 319–330, Springer.
Mihalcea, R., Liu, H., & Lieberman, H. (2006). NLP (natural language processing) for NLP (natural language programming). In A. Gelbukh (Ed.), Computational Linguistics and Intelligent Text Processing (LNCS 3878, pp. 319–330). Springer.
@incollection{mihalcea2006nlp,
author = {Rada Mihalcea and Hugo Liu and Henry Lieberman},
title = {NLP (natural language processing) for NLP (natural language programming)},
booktitle = {Computational Linguistics and Intelligent Text Processing},
editor = {A. Gelbukh},
series = {LNCS 3878},
pages = {319--330},
publisher = {Springer},
doi = {10.1007/11671299_34},
url = {https://starheartsong.com/papers/pdf/CICLING2006-NLP4NLP.pdf},
year = {2006}
}This paper asks how much program structure can be recovered from ordinary English while preserving language's useful incompleteness. It combines Metafor's mappings with detectors for steps, loops, examples, conditions, passive statements, and assumptions, then emits Perl-like scaffolding. The evaluation began with 120 introductory programming assignments gathered from the web; twenty-five were manually annotated. Step detection reached 86.0 percent precision and 75.4 percent recall, while loop detection reached 80.6 percent precision and 71.4 percent recall. The output is deliberately an outline, not complete runnable software. Its rules depend on surface cues and the conventions of classroom assignments, some potentially executable statements become comments, and the study does not ask whether learners finish programs more successfully with the generated skeletons.