A5032297025- Software Engineering Research
- Software Engineering Techniques and Practices
- Topic Modeling
- Software System Performance and Reliability
- Advanced Text Analysis Techniques
- Sentiment Analysis and Opinion Mining
- Multimodal Machine Learning Applications
- Open Source Software Innovations
- Software Reliability and Analysis Research
- Domain Adaptation and Few-Shot Learning
Universitat Politècnica de Catalunya
2018-2021
Continual learning (CL) aims to enable information systems learn from a continuous data stream across time. However, it is difficult for existing deep architectures new task without largely forgetting previously acquired knowledge. Furthermore, CL particularly challenging language learning, as natural ambiguous: discrete, compositional, and its meaning context-dependent. In this work, we look at the problem of through lens various NLP tasks. Our survey discusses major challenges in current...
Context: Incomplete or incorrect detection of requirement dependencies has proven to result in reduced release quality and substantial rework. Additionally, the extraction is challenging since requirements are mostly documented natural language, which makes it a cognitively difficult task. Moreover, with ever-changing new requirements, manual analysis process must be repeated, imposes extra hardship even for domain experts. Objective: The three main objectives this research are: 1) Proposing...
Abstract People express their opinions and views in different often ambiguous ways, hence the meaning of words is not explicitly stated frequently depends on context. Therefore, it difficult for machines to process understand information conveyed human languages. This work addresses problem sentiment analysis (SA). We propose a simple yet comprehensive method which uses contextual embeddings self-attention mechanism detect classify sentiment. perform experiments reviews from domains, as well...
Conducting empirical research in software engineering industry is a process, and as such, it should be generalizable. The aim of this paper to discuss how academic researchers may address some the challenges they encounter during conducting by means systematic structured approach. protocol developed serve practical guide for help them with complex environment.
Context: Coordination in large-scale software development is critical yet difficult, as it faces the problem of dependency management and resolution. In this work, we focus on managing requirement dependencies that Agile (ASD) come form user stories. Objective: This work studies decisions teams regarding identification between Our goal to explain detection through users' behavior large-scale, distributed projects. Method: We perform empirical evaluation a large real-world dataset from an...