%0 Conference Paper %1 Anquetil1998b %A Anquetil, N. %A Lethbridge, T. %B Proc. Int'l Conf. on Software Engineering. %D 1998 %I IEEE %K software source maintenance AI code to_read abbreviations engineering %P 84--93 %R 10.1109/ICSE.1998.671105 %T Extracting concepts from file names; a new file clustering criterion %X Decomposing complex software systems into conceptually independent subsystems is a significant software engineering activity which received considerable research attention. Most of the research in this domain considers the body of the source code; trying to cluster together files which are conceptually related. We discuss techniques for extracting concepts (abbreviations) from a more informal source of information: file names. The task is difficult because nothing indicates where to split the file names into substrings. In general, finding abbreviations would require domain knowledge to identify the concepts that are referred to in a name and intuition to recognize such concepts in abbreviated forms. We show by experiment that the techniques we propose allow about 90% of the abbreviations to be found automatically

@inproceedings{Anquetil1998b, abstract = {Decomposing complex software systems into conceptually independent subsystems is a significant software engineering activity which received considerable research attention. Most of the research in this domain considers the body of the source code; trying to cluster together files which are conceptually related. We discuss techniques for extracting concepts (abbreviations) from a more informal source of information: file names. The task is difficult because nothing indicates where to split the file names into substrings. In general, finding abbreviations would require domain knowledge to identify the concepts that are referred to in a name and intuition to recognize such concepts in abbreviated forms. We show by experiment that the techniques we propose allow about 90% of the abbreviations to be found automatically}, added-at = {2009-12-15T20:25:25.000+0100}, author = {Anquetil, N. and Lethbridge, T.}, biburl = {https://www.bibsonomy.org/bibtex/2ef40801ec4f970b0a9e3959818fa7f00/sjbutler}, booktitle = {Proc. Int'l Conf. on Software Engineering.}, doi = {10.1109/ICSE.1998.671105}, interhash = {27ca8d61f25fd0be1e365f13cbc2ff45}, intrahash = {ef40801ec4f970b0a9e3959818fa7f00}, issn = {0270-5257}, keywords = {software source maintenance AI code to_read abbreviations engineering}, month = Apr, pages = {84--93}, publisher = {IEEE}, timestamp = {2009-12-15T20:25:25.000+0100}, title = {Extracting concepts from file names; a new file clustering criterion}, year = 1998 }