%0 Conference Paper %1 8049173 %A Ferrari, A. %A Spagnolo, G. O. %A Gnesi, S. %B 2017 IEEE 25th International Requirements Engineering Conference (RE) %D 2017 %K dataset web %P 502-505 %R 10.1109/RE.2017.29 %T PURE: A Dataset of Public Requirements Documents %U https://ieeexplore.ieee.org/abstract/document/8049173 %X This paper presents PURE (PUblic REquirements dataset), a dataset of 79 publicly available natural language requirements documents collected from the Web. The dataset includes 34,268 sentences and can be used for natural language processing tasks that are typical in requirements engineering, such as model synthesis, abstraction identification and document structure assessment. It can be further annotated to work as a benchmark for other tasks, such as ambiguity detection, requirements categorisation and identification of equivalent re-quirements. In the paper, we present the dataset and we compare its language with generic English texts, showing the peculiarities of the requirements jargon, made of a restricted vocabulary of domain-specific acronyms and words, and long sentences. We also present the common XML format to which we have manually ported a subset of the documents, with the goal of facilitating replication of NLP experiments.

@inproceedings{8049173, abstract = {This paper presents PURE (PUblic REquirements dataset), a dataset of 79 publicly available natural language requirements documents collected from the Web. The dataset includes 34,268 sentences and can be used for natural language processing tasks that are typical in requirements engineering, such as model synthesis, abstraction identification and document structure assessment. It can be further annotated to work as a benchmark for other tasks, such as ambiguity detection, requirements categorisation and identification of equivalent re-quirements. In the paper, we present the dataset and we compare its language with generic English texts, showing the peculiarities of the requirements jargon, made of a restricted vocabulary of domain-specific acronyms and words, and long sentences. We also present the common XML format to which we have manually ported a subset of the documents, with the goal of facilitating replication of NLP experiments.}, added-at = {2021-01-21T15:59:24.000+0100}, author = {{Ferrari}, A. and {Spagnolo}, G. O. and {Gnesi}, S.}, biburl = {https://www.bibsonomy.org/bibtex/2b31ddd86046942f65a80dee511a00a58/parismic}, booktitle = {2017 IEEE 25th International Requirements Engineering Conference (RE)}, description = {PURE: A Dataset of Public Requirements Documents - IEEE Conference Publication}, doi = {10.1109/RE.2017.29}, interhash = {dfadf895cf3a7ee20956ca59e13152f4}, intrahash = {b31ddd86046942f65a80dee511a00a58}, issn = {2332-6441}, keywords = {dataset web}, month = {Sep.}, pages = {502-505}, timestamp = {2021-01-21T15:59:24.000+0100}, title = {PURE: A Dataset of Public Requirements Documents}, url = {https://ieeexplore.ieee.org/abstract/document/8049173}, year = 2017 }