Summary of Language Model Meets Prototypes: Towards Interpretable Text Classification Models Through Prototypical Networks, by Ximing Wen
Language Model Meets Prototypes: Towards Interpretable Text Classification Models through Prototypical Networks
by Ximing Wen
First submitted to arxiv on: 4 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 A novel approach is proposed for developing intrinsically interpretable language models while maintaining their superior performance. Prototypical networks are used as encoders to capture sentiment incongruity and enhance accuracy, offering instance-based explanations for classification decisions. A white-box multi-head graph attention-based prototype network is designed to explain the decisions of text classification models without sacrificing accuracy. The approach is extended with contrastive learning to enhance both interpretability and performance in document classification tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way is found to make language models more understandable while keeping them good at their job. The idea uses “prototypes” to capture the main point of some text and explain why a model made a certain decision. This helps to fix the problem of these models being too hard to understand. A special kind of attention-based network is designed to do this without losing any accuracy. |
Keywords
» Artificial intelligence » Attention » Classification » Text classification
