Rationalizing Neural Predictions

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.

Learning to Skim Text

“…The key difference between our work and Lei et al (2016)'s method is that our method optimizes for faster inference, and is more dynamic in its jumping. Likewise is the difference between our approach and the "soft" attention approach by (Bahdanau et al, 2014).…”

Open-Domain Neural Conversational Agents: The Step Towards Artificial General Intelligence

“…The ideal complex neural conversational model should yield improved performances and offer interpretable rationales for answer predictions. Current cutting-edge approach presented in [23], incorporate rationale generation as an integral part of the learning problem. This approach limit the models to extractive rationales by limiting the rationales to be subsets of words from input text that are short and coherent or must alone suffice for prediction as a substitute of the original text.…”

Tell Me Why: Using Question Answering as Distant Supervision for Answer Justification

“…In many ways, deep learning has become the canonical example of the "black box" of machine learning and many of the approaches to explaining it can be loosely categorized into two types: approaches that try to interpret the parameters themselves (e.g., with visualizations and heat maps (Zeiler and Fergus, 2014;Hermann et al, 2015;Li et al, 2016), and approaches that generate humaninterpretable information that is ideally correlated with what is being learned inside the model (e.g., Lei et al (2016) Deep learning has been successfully applied to many recent QA approaches and related tasks (Bordes et al, 2015;Hermann et al, 2015;He and Golub, 2016;Dong et al, 2015;Tan et al, 2016, inter alia). However, large quantities of data are needed to train the millions of parameters often contained in these models.…”

“…One approach to interpreting complex models is to make use of human-interpretable information generated by the model to gain insight into what the model is learning. We follow the intuition of Lei et al (2016), whose two-component network first generates text spans from an input document, and then uses these text spans to make predictions. Lei et al utilize these intermediate text spans to infer the model's preferences.…”