Rationalizing Neural Predictions
read the original abstract
Prediction without justification has limited applicability. As a remedy, we learn to extract pieces of input text as justifications -- rationales -- that are tailored to be short and coherent, yet sufficient for making the same prediction. Our approach combines two modular components, generator and encoder, which are trained to operate well together. The generator specifies a distribution over text fragments as candidate rationales and these are passed through the encoder for prediction. Rationales are never given during training. Instead, the model is regularized by desiderata for rationales. We evaluate the approach on multi-aspect sentiment analysis against manually annotated test cases. Our approach outperforms attention-based baseline by a significant margin. We also successfully illustrate the method on the question retrieval task.
This paper has not been read by Pith yet.
Forward citations
Cited by 5 Pith papers
-
Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
-
HuggingFace's Transformers: State-of-the-art Natural Language Processing
Hugging Face releases an open-source Python library that supplies a unified API and pretrained weights for major Transformer architectures used in natural language processing.
-
Towards A Rigorous Science of Interpretable Machine Learning
The authors define interpretability for machine learning, specify when it is required, and propose a taxonomy for its rigorous evaluation while identifying open research questions.
-
Visual Interaction with Deep Learning Models through Collaborative Semantic Inference
Proposes the CSI framework for co-designing visual interactions and deep learning models to expose and allow semantic control over intermediate reasoning processes, shown in a summarization case study.
-
Learning Patient Engagement in Care Management: Performance vs. Interpretability
A behavioral engagement scoring method predicts patient response propensity in care management using real-world data and supplies interpretable insights via prototypical patients without performance loss.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.