Inherent Characteristics of Traceability Artifacts: Less Is More. Hayes, J. H., Antoniol, G., Adams, B., & Guéhéneuc, Y. In Zowghi, D. & Gervasi, V., editors, Proceedings of the 23<sup>rd</sup> International Requirements Engineering Conference (RE), pages 196–201, August, 2015. IEEE CS Press. RE Next! 6 pages.Paper abstract bibtex This paper describes ongoing work to characterize the inherent ease or ``traceability'' with which a textual artifact can be traced using an automated technique. Software traceability approaches use varied measures to build models that automatically recover links between pairs of natural language documents. Thus far, most of the approaches use a single-step model, such as logistic regression, to identify new trace links. However, such approaches require a large enough training set of both true and false trace links. Yet, the former are by far in the minority, which reduces the performance of such models. Therefore, this paper formulates the problem of identifying trace links as the problem of finding, for a given logistic regression model, the subsets of links in the training set giving the best accuracy (in terms of G-metric) on a test set. Using hill climbing with random restart for subset selection, we found that, for the ChangeStyle dataset, we can classify links with a precision of up to 40% and a recall of up to 66% using a training set as small as one true candidate link (out of 33) and 41 false links. To get better performance and learn the best possible logistic regression classifier, we must ``discard'' links in the trace dataset that increase noise to avoid learning with links that are not representative. This preliminary work is promising because it shows that few correct examples may perform better than several poor ones. It also shows which inherent characteristics of the artifacts make them good candidates to learn efficient traceability models automatically, i.e., it reveals their traceability.
@INPROCEEDINGS{Hayes15-RENext-InherentCharacteristics,
author = {Jane Huffman Hayes and Giuliano Antoniol and Bram Adams and Yann-Ga{\"e}l Gu{\'e}h{\'e}neuc},
title = {Inherent Characteristics of Traceability Artifacts: Less Is More},
booktitle = {Proceedings of the 23<sup>{rd}</sup> International Requirements Engineering Conference ({RE})},
pages = {196--201},
note = {RE Next! 6 pages.},
comment = {RE Next!},
year = {2015},
month = {August},
editor = {Didar Zowghi and Vincenzo Gervasi},
publisher = {IEEE CS Press},
abstract = {This paper describes ongoing work to characterize the inherent ease or ``traceability'' with which a textual artifact can be traced using an automated technique. Software traceability approaches use varied measures to build models that automatically recover links between pairs of natural language documents. Thus far, most of the approaches use a single-step model, such as logistic regression, to identify new trace links. However, such approaches require a large enough training set of both true and false trace links. Yet, the former are by far in the minority, which reduces the performance of such models. Therefore, this paper formulates the problem of identifying trace links as the problem of finding, for a given logistic regression model, the subsets of links in the training set giving the best accuracy (in terms of G-metric) on a test set. Using hill climbing with random restart for subset selection, we found that, for the ChangeStyle dataset, we can classify links with a precision of up to 40\% and a recall of up to 66\% using a training set as small as one true candidate link (out of 33) and 41 false links. To get better performance and learn the best possible logistic regression classifier, we must ``discard'' links in the trace dataset that increase noise to avoid learning with links that are not representative. This preliminary work is promising because it shows that few correct examples may perform better than several poor ones. It also shows which inherent characteristics of the artifacts make them good candidates to learn efficient traceability models automatically, i.e., it reveals their traceability.},
grant = {NSERC DG and CRC on Software Patterns},
keywords = {Understanding program comprehension ; RE},
kind = {MIADR},
language = {english},
url = {http://www.ptidej.net/publications/documents/RENext15.doc.pdf},
pdf = {http://www.ptidej.net/publications/documents/RENext15.ppt.pdf}
}
Downloads: 0
{"_id":"B5tfLXTdbzCmwA4gE","bibbaseid":"hayes-antoniol-adams-guhneuc-inherentcharacteristicsoftraceabilityartifactslessismore-2015","downloads":0,"creationDate":"2018-01-17T20:29:42.224Z","title":"Inherent Characteristics of Traceability Artifacts: Less Is More","author_short":["Hayes, J. H.","Antoniol, G.","Adams, B.","Guéhéneuc, Y."],"year":2015,"bibtype":"inproceedings","biburl":"http://www.yann-gael.gueheneuc.net/Work/BibBase/guehene (automatically cleaned).bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Jane","Huffman"],"propositions":[],"lastnames":["Hayes"],"suffixes":[]},{"firstnames":["Giuliano"],"propositions":[],"lastnames":["Antoniol"],"suffixes":[]},{"firstnames":["Bram"],"propositions":[],"lastnames":["Adams"],"suffixes":[]},{"firstnames":["Yann-Gaël"],"propositions":[],"lastnames":["Guéhéneuc"],"suffixes":[]}],"title":"Inherent Characteristics of Traceability Artifacts: Less Is More","booktitle":"Proceedings of the 23<sup>rd</sup> International Requirements Engineering Conference (RE)","pages":"196–201","note":"RE Next! 6 pages.","comment":"RE Next!","year":"2015","month":"August","editor":[{"firstnames":["Didar"],"propositions":[],"lastnames":["Zowghi"],"suffixes":[]},{"firstnames":["Vincenzo"],"propositions":[],"lastnames":["Gervasi"],"suffixes":[]}],"publisher":"IEEE CS Press","abstract":"This paper describes ongoing work to characterize the inherent ease or ``traceability'' with which a textual artifact can be traced using an automated technique. Software traceability approaches use varied measures to build models that automatically recover links between pairs of natural language documents. Thus far, most of the approaches use a single-step model, such as logistic regression, to identify new trace links. However, such approaches require a large enough training set of both true and false trace links. Yet, the former are by far in the minority, which reduces the performance of such models. Therefore, this paper formulates the problem of identifying trace links as the problem of finding, for a given logistic regression model, the subsets of links in the training set giving the best accuracy (in terms of G-metric) on a test set. Using hill climbing with random restart for subset selection, we found that, for the ChangeStyle dataset, we can classify links with a precision of up to 40% and a recall of up to 66% using a training set as small as one true candidate link (out of 33) and 41 false links. To get better performance and learn the best possible logistic regression classifier, we must ``discard'' links in the trace dataset that increase noise to avoid learning with links that are not representative. This preliminary work is promising because it shows that few correct examples may perform better than several poor ones. It also shows which inherent characteristics of the artifacts make them good candidates to learn efficient traceability models automatically, i.e., it reveals their traceability.","grant":"NSERC DG and CRC on Software Patterns","keywords":"Understanding program comprehension ; RE","kind":"MIADR","language":"english","url":"http://www.ptidej.net/publications/documents/RENext15.doc.pdf","pdf":"http://www.ptidej.net/publications/documents/RENext15.ppt.pdf","bibtex":"@INPROCEEDINGS{Hayes15-RENext-InherentCharacteristics,\n author = {Jane Huffman Hayes and Giuliano Antoniol and Bram Adams and Yann-Ga{\\\"e}l Gu{\\'e}h{\\'e}neuc},\n title = {Inherent Characteristics of Traceability Artifacts: Less Is More},\n booktitle = {Proceedings of the 23<sup>{rd}</sup> International Requirements Engineering Conference ({RE})},\n pages = {196--201},\n note = {RE Next! 6 pages.},\n comment = {RE Next!},\n year = {2015},\n month = {August},\n editor = {Didar Zowghi and Vincenzo Gervasi},\n publisher = {IEEE CS Press},\n abstract = {This paper describes ongoing work to characterize the inherent ease or ``traceability'' with which a textual artifact can be traced using an automated technique. Software traceability approaches use varied measures to build models that automatically recover links between pairs of natural language documents. Thus far, most of the approaches use a single-step model, such as logistic regression, to identify new trace links. However, such approaches require a large enough training set of both true and false trace links. Yet, the former are by far in the minority, which reduces the performance of such models. Therefore, this paper formulates the problem of identifying trace links as the problem of finding, for a given logistic regression model, the subsets of links in the training set giving the best accuracy (in terms of G-metric) on a test set. Using hill climbing with random restart for subset selection, we found that, for the ChangeStyle dataset, we can classify links with a precision of up to 40\\% and a recall of up to 66\\% using a training set as small as one true candidate link (out of 33) and 41 false links. To get better performance and learn the best possible logistic regression classifier, we must ``discard'' links in the trace dataset that increase noise to avoid learning with links that are not representative. This preliminary work is promising because it shows that few correct examples may perform better than several poor ones. It also shows which inherent characteristics of the artifacts make them good candidates to learn efficient traceability models automatically, i.e., it reveals their traceability.},\n grant = {NSERC DG and CRC on Software Patterns},\n keywords = {Understanding program comprehension ; RE},\n kind = {MIADR},\n language = {english},\n url = {http://www.ptidej.net/publications/documents/RENext15.doc.pdf},\n pdf = {http://www.ptidej.net/publications/documents/RENext15.ppt.pdf}\n}\n\n","author_short":["Hayes, J. H.","Antoniol, G.","Adams, B.","Guéhéneuc, Y."],"editor_short":["Zowghi, D.","Gervasi, V."],"key":"Hayes15-RENext-InherentCharacteristics","id":"Hayes15-RENext-InherentCharacteristics","bibbaseid":"hayes-antoniol-adams-guhneuc-inherentcharacteristicsoftraceabilityartifactslessismore-2015","role":"author","urls":{"Paper":"http://www.ptidej.net/publications/documents/RENext15.doc.pdf"},"keyword":["Understanding program comprehension ; RE"],"metadata":{"authorlinks":{"gu�h�neuc, y":"https://bibbase.org/show?bib=http%3A%2F%2Fwww.yann-gael.gueheneuc.net%2FWork%2FPublications%2FBiblio%2Fcomplete-bibliography.bib&msg=embed","guéhéneuc, y":"https://bibbase.org/show?bib=http://www.yann-gael.gueheneuc.net/Work/BibBase/guehene%20(automatically%20cleaned).bib"}},"downloads":0,"html":""},"search_terms":["inherent","characteristics","traceability","artifacts","less","more","hayes","antoniol","adams","guéhéneuc"],"keywords":["understanding program comprehension ; re"],"authorIDs":["AfJhKcg96muyPdu7S","xkviMnkrGBneANvMr"],"dataSources":["Sed98LbBeGaXxenrM","8vn5MSGYWB4fAx9Z4"]}