Advancing Interpretability in Text Classification through Prototype Learning
This addresses the problem of transparency in text classification for applications where interpretability is critical, representing an incremental improvement over existing prototype-based methods.
The paper tackles the lack of interpretability in deep neural networks for text classification by proposing ProtoLens, a prototype-based model that provides fine-grained, sub-sentence level interpretability while maintaining competitive accuracy, as shown by outperforming baselines on multiple benchmarks.
Deep neural networks have achieved remarkable performance in various text-based tasks but often lack interpretability, making them less suitable for applications where transparency is critical. To address this, we propose ProtoLens, a novel prototype-based model that provides fine-grained, sub-sentence level interpretability for text classification. ProtoLens uses a Prototype-aware Span Extraction module to identify relevant text spans associated with learned prototypes and a Prototype Alignment mechanism to ensure prototypes are semantically meaningful throughout training. By aligning the prototype embeddings with human-understandable examples, ProtoLens provides interpretable predictions while maintaining competitive accuracy. Extensive experiments demonstrate that ProtoLens outperforms both prototype-based and non-interpretable baselines on multiple text classification benchmarks. Code and data are available at \url{https://anonymous.4open.science/r/ProtoLens-CE0B/}.