Write a Blog >>
ICSE 2022
Sun 8 - Fri 27 May 2022
Sun 8 May 2022 11:50 - 12:10 at NLBSE room - Paper Session 2 Chair(s): Andrea Di Sorbo, Sebastiano Panichella

Neural Machine Translation (NMT) has reached a level of maturity to be recognized as the premier method for the translation between different languages and aroused interest in different research areas, including software engineering. A key step to validate the robustness of the NMT models consists in evaluating the performance of the models on adversarial inputs, i.e., inputs obtained from the original ones by adding small amounts of perturbation. However, the robustness assessment of NMT is a large and still open problem since there is not yet an approach for evaluating the robustness of the models used for the code generation task (i.e., generating a program from its description in natural language). In this work, we address the problem by identifying a set of perturbations and metrics tailored for the robustness assessment of such models. We present a preliminary experimental evaluation, showing what type of perturbations affect the model the most and deriving useful insights for future directions.

Sun 8 May

Displayed time zone: Eastern Time (US & Canada) change

11:20 - 12:45
Paper Session 2NLBSE at NLBSE room
Chair(s): Andrea Di Sorbo University of Sannio, Sebastiano Panichella Zurich University of Applied Sciences
On the Evaluation of NLP-based Models for Software Engineering
Maliheh Izadi Delft University of Technology, Matin Nili Ahmadabadi University of Tehran
Identification of Intra-Domain Ambiguity using Transformer-based Machine Learning
Ambarish Moharil Eindhoven University of Technology, Arpit Sharma
Can NMT Understand Me? Towards Perturbation-based Evaluation of NMT Models for Code Generation
Pietro Liguori University of Naples Federico II, Cristina Improta University of Naples Federico II, Simona De Vivo University of Naples Federico II, Roberto Natella Federico II University of Naples, Bojan Cukic University of North Carolina at Charlotte, Domenico Cotroneo University of Naples Federico II
Supporting Systematic Literature Reviews Using Deep-Learning-Based Language Models
Rand Alchokr Otto von Guericke University, Manoj Borkar , Sharanya Thotadarya otto von Guericke University, Thomas Leich Harz University of Applied Sciences, Germany, Gunter Saake Otto von Guericke University
Story Point Level Classification by Text Level Graph Neural Network
Hung Phan , Ali Jannesari Iowa State University

Information for Participants
Sun 8 May 2022 11:20 - 12:45 at NLBSE room - Paper Session 2 Chair(s): Andrea Di Sorbo, Sebastiano Panichella
Info for room NLBSE room:

Click here to go to the room on Midspace