TY - CHAP

T1 - Extracting Software Requirements from Unstructured Documents

AU - Ivanov, Vladimir

AU - Sadovykh, Andrey

AU - Naumchev, Alexandr

AU - Bagnato, Alessandra

AU - Yakovlev, Kirill

PY - 2022/8/30

Y1 - 2022/8/30

N2 - Requirements identification in textual documents or extraction is a tedious and error prone task that many researchers suggest automating. We manually annotated the PURE dataset and thus created a new one containing both requirements and non-requirements. Using this dataset, we fine-tuned the BERT model and compare the results with several baselines such as fastText and ELMo. In order to evaluate the model on semantically more complex documents we compare the PURE dataset results with experiments on Request For Information (RFI) documents. The RFIs often include software requirements, but in a less standardized way. The fine-tuned BERT showed promising results on PURE dataset on the binary sentence classification task. Comparing with previous and recent studies dealing with constrained inputs, our approach demonstrates high performance in terms of precision and recall metrics, while being agnostic to the unstructured textual input.

AB - Requirements identification in textual documents or extraction is a tedious and error prone task that many researchers suggest automating. We manually annotated the PURE dataset and thus created a new one containing both requirements and non-requirements. Using this dataset, we fine-tuned the BERT model and compare the results with several baselines such as fastText and ELMo. In order to evaluate the model on semantically more complex documents we compare the PURE dataset results with experiments on Request For Information (RFI) documents. The RFIs often include software requirements, but in a less standardized way. The fine-tuned BERT showed promising results on PURE dataset on the binary sentence classification task. Comparing with previous and recent studies dealing with constrained inputs, our approach demonstrates high performance in terms of precision and recall metrics, while being agnostic to the unstructured textual input.

KW - BERT

KW - ELMo

KW - FastText

KW - Requirements elicitation

KW - Sentence classification

KW - Software requirements

UR - https://www.mendeley.com/catalogue/e7bd97ea-a8bd-3d98-b281-aeee3efbb657/

U2 - 10.1007/978-3-031-15168-2_2

DO - 10.1007/978-3-031-15168-2_2

M3 - Chapter

SN - 978-3-031-15167-5

T3 - Recent Trends in Analysis of Images, Social Networks and Texts

SP - 17

EP - 29

BT - Extracting Software Requirements from Unstructured Documents

PB - Springer

ER -