Requirements Classification with Interpretable Machine Learning and Dependency Parsing

Requirements Classification with Interpretable Machine Learning and Dependency Parsing. Dalpiaz, F., Dell'Anna, D., Aydemir, F. B., & Çevikol, S. In Proceedings of the 27th IEEE International Requirements Engineering Conference, RE 2019, pages 142–152, 2019.

Link

Requirements Classification with Interpretable Machine Learning and Dependency Parsing [pdf]

Paper

Slides

Supplement doi abstract bibtex 4 downloads

Requirements classification is a traditional application of machine learning (ML) to RE that helps handle large requirements datasets. A prime example of an RE classification problem is the distinction between functional and non-functional (quality) requirements. State-of-the-art classifiers build their effectiveness on a large set of word features like text n-grams or POS n-grams, which do not fully capture the essence of a requirement. As a result, it is arduous for human analysts to interpret the classification results by exploring the classifier's inner workings. We propose the use of more general linguistic features, such as dependency types, for the construction of interpretable ML classifiers for RE. Through a feature engineering effort, in which we are assisted by modern introspection tools that reveal the hidden inner workings of ML classifiers, we derive a set of 17 linguistic features. While classifiers that use our proposed features fit the training set slightly worse than those that use high-dimensional feature sets, our approach performs generally better on validation datasets and it is more interpretable.

@inproceedings{DBLP:conf/re/DalpiazDAC19,
  author    = {Fabiano Dalpiaz and
               Davide Dell'Anna and
               Fatma Başak Aydemir and
               Sercan {\c{C}}evikol},
  title     = {Requirements Classification with Interpretable Machine Learning and
               Dependency Parsing},
  booktitle = {Proceedings of the 27th {IEEE} International Requirements Engineering Conference, {RE}
               2019},
  pages     = {142--152},
  year      = {2019},
  url_Link       = {https://doi.org/10.1109/RE.2019.00025},
  url_Paper      = {2019_RE/RE19_Dalpiaz.pdf},
  url_Slides= {2019_RE/RE19_Dalpiaz_Slides.pdf},
  url_Supplement = {https://doi.org/10.5281/zenodo.3309582},
  doi       = {10.1109/RE.2019.00025},
  keywords  = {Requirements, Requirements Classification, Machine Learning, Classification, Dependency Parsing, NLP4RE},
  timestamp = {Mon, 15 Jun 2020 01:00:00 +0200},
  biburl    = {https://dblp.org/rec/conf/re/DalpiazDAC19.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org},
  abstract = {Requirements classification is a traditional application of machine learning (ML) to RE that helps handle large requirements datasets. A prime example of an RE classification problem is the distinction between functional and non-functional (quality) requirements. 
                  State-of-the-art classifiers build their effectiveness on a large set of word features like text n-grams or POS n-grams, which do not fully capture the essence of a requirement. As a result, it is arduous for human analysts to interpret the classification results by exploring the classifier's inner workings. 
                  We propose the use of more general linguistic features, such as dependency types, for the construction of interpretable ML classifiers for RE. Through a feature engineering effort, in which we are assisted by modern introspection tools that reveal the hidden inner workings of ML classifiers, we derive a set of 17 linguistic features.
                  While classifiers that use our proposed features fit the training set slightly worse than those that use high-dimensional feature sets, our approach performs generally better on validation datasets and it is more interpretable.}
}

Downloads: 4