Summary of Effective Black Box Testing Of Sentiment Analysis Classification Networks, by Parsa Karbasizadeh et al.
Effective Black Box Testing of Sentiment Analysis Classification Networks
by Parsa Karbasizadeh, Fathiyeh Faghih, Pouria Golshanrad
First submitted to arxiv on: 30 Jul 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Software Engineering (cs.SE)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a set of novel coverage criteria for testing transformer-based neural networks used in sentiment analysis tasks. It leverages input space partitioning and the k-projection coverage metric to generate tests that cover a wide range of emotional features. The approach utilizes large language models to create sentences with specific combinations of emotional elements. Experimental results on a sentiment analysis dataset show an average increase of 16% in test coverage, accompanied by a corresponding decrease of 6.5% in model accuracy. This highlights the ability to identify vulnerabilities and improve the dependability of transformer-based sentiment analysis systems. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper develops new ways to check how well computer programs can understand emotions in text. It uses special techniques to make sure these programs are thorough and reliable. The researchers use big language models to create sentences that show different emotional features, like verbs or adjectives. This helps them test the programs’ abilities and find where they might go wrong. |
Keywords
» Artificial intelligence » Transformer
