Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-11390
For citation please use:
Main Title: Improving Trace Link Recovery using Semantic Relation Graphs and Spreading Activation
Author(s): Schlutter, Aaron
Vogelsang, Andreas
Type: Conference Object
References: 10.14279/depositonce-7776
10.14279/depositonce-9772.2
10.14279/depositonce-10207.2
Language Code: en
Abstract: [Context & Motivation] Trace Link Recovery tries to identify and link related existing requirements with each other to support further engineering tasks. Existing approaches are mainly based on algebraic Information Retrieval or machine-learning. [Question/Problem] Machine-learning approaches usually demand reasonably large and labeled datasets to train. Algebraic Information Retrieval approaches like distance between tf - idf scores also work on smaller datasets without training but are limited in considering the context of semantic statements. [Principal Ideas/Results] In this work, we revise our existing Trace Link Recovery approach that is based on an explicit representation of the content of requirements as a semantic relation graph and uses Spreading Activation to answer trace queries over this graph. The approach generates sorted candidate lists and is fully automated including an NLP pipeline to transform unrestricted natural language requirements into a graph and does not require any external knowledge bases or other resources. [Contribution] To improve the performance, we take a detailed look at five common datasets and adapt the graph structure and semantic search algorithm. Depending on the selected configuration, the predictive power strongly varies. With the best tested configuration, the approach achieves a mean average precision of 50%, a Lag of 30%, and a recall of 90%.
URI: https://depositonce.tu-berlin.de/handle/11303/12581
http://dx.doi.org/10.14279/depositonce-11390
Issue Date: 16-Feb-2021
Date Available: 12-Feb-2021
DDC Class: 006 Spezielle Computerverfahren
Subject(s): traceability
trace link recovery
natural language processing
spreading activation
semantic relation graph
information retrieval
NLP
License: http://rightsstatements.org/vocab/InC/1.0/
Proceedings Title: 27th International Working Conference on Requirement Engineering: Foundation for Software Quality (REFSQ 2021)
Appears in Collections:FG IT-basierte Fahrzeuginnovationen » Publications

Files in This Item:
schlutter_vogelsang_REFSQ2021.pdf

Accepted manuscript

Format: Adobe PDF | Size: 1.45 MB
DownloadShow Preview
Thumbnail

Item Export Bar

Items in DepositOnce are protected by copyright, with all rights reserved, unless otherwise indicated.