On- and Off-Topic Classification and Semantic Annotation of User-Generated Software Requirements

M. Dollmann, M. Geierhos, in: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics (ACL), Austin, TX, USA, 2016, pp. 1807–1816.

Download
Restricted 176-D16-1186.pdf 259.50 KB
Conference Paper | Published | English
Abstract
Users prefer natural language software requirements because of their usability and accessibility. When they describe their wishes for software development, they often provide off-topic information. We therefore present an automated approach for identifying and semantically annotating the on-topic parts of the given descriptions. It is designed to support requirement engineers in the requirement elicitation process on detecting and analyzing requirements in user-generated content. Since no lexical resources with domain-specific information about requirements are available, we created a corpus of requirements written in controlled language by instructed users and uncontrolled language by uninstructed users. We annotated these requirements regarding predicate-argument structures, conditions, priorities, motivations and semantic roles and used this information to train classifiers for information extraction purposes. The approach achieves an accuracy of 92% for the on- and off-topic classification task and an F1-measure of 72% for the semantic annotation.
Publishing Year
Proceedings Title
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Page
1807-1816
Conference
Conference on Empirical Methods in Natural Language Processing (EMNLP 2016)
Conference Location
Austin, TX, USA
Conference Date
2016-11-01 – 2016-11-05
LibreCat-ID

Cite this

Dollmann M, Geierhos M. On- and Off-Topic Classification and Semantic Annotation of User-Generated Software Requirements. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP). Austin, TX, USA: Association for Computational Linguistics (ACL); 2016:1807-1816.
Dollmann, M., & Geierhos, M. (2016). On- and Off-Topic Classification and Semantic Annotation of User-Generated Software Requirements. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 1807–1816). Austin, TX, USA: Association for Computational Linguistics (ACL).
@inproceedings{Dollmann_Geierhos_2016, place={Austin, TX, USA}, title={On- and Off-Topic Classification and Semantic Annotation of User-Generated Software Requirements}, booktitle={Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, publisher={Association for Computational Linguistics (ACL)}, author={Dollmann, Markus and Geierhos, Michaela}, year={2016}, pages={1807–1816} }
Dollmann, Markus, and Michaela Geierhos. “On- and Off-Topic Classification and Semantic Annotation of User-Generated Software Requirements.” In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1807–16. Austin, TX, USA: Association for Computational Linguistics (ACL), 2016.
M. Dollmann and M. Geierhos, “On- and Off-Topic Classification and Semantic Annotation of User-Generated Software Requirements,” in Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP), Austin, TX, USA, 2016, pp. 1807–1816.
Dollmann, Markus, and Michaela Geierhos. “On- and Off-Topic Classification and Semantic Annotation of User-Generated Software Requirements.” Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP), Association for Computational Linguistics (ACL), 2016, pp. 1807–16.
Main File(s)
File Name
176-D16-1186.pdf 259.50 KB
Access Level
Restricted Closed Access
Last Uploaded
2018-03-21T12:33:48Z


Link(s) to Main File(s)
Access Level
Restricted Closed Access

Export

Marked Publications

Open Data LibreCat

Search this title in

Google Scholar