Towards Interpretable Natural Language Understanding with Explanations as Latent Variables

By Wangchunshu Zhou, Jinyi Hu, Hanlin Zhang, Xiaodan Liang, Maosong Sun, Chenyan Xiong, Jian Tang. 2020

50 citations recorded by the source corpus.

Recently generating natural language explanations has shown very promising results in not only offering interpretable explanations but also providing additional information and supervision for prediction. However, existing approaches usually require a large set of human annotated explanations for training while collecting a large set of explanations is not only time consuming but also expensive. In this paper, we develop a general framework for interpretable natural language understanding that requires only a small set of human annotated explanations for training. Our framework treats natural language explanations as latent variables that model the underlying reasoning process of a neural model. We develop a variational EM framework for optimization where an explanation generation module and an explanation-augmented prediction module are alternatively optimized and mutually enhance each other. Moreover, we further propose an explanation-based self-training method under this framework for semi-supervised learning. It alternates between assigning pseudo-labels to unlabeled data and generating new explanations to iteratively improve each other. Experiments on two natural language understanding tasks demonstrate that our framework can not only make effective predictions in both supervised and semi-supervised settings, but also generate good natural language explanation.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Chain of Thought Prompting Elicits Reasoning in Large Language Models (2022, neutral): “Another closely related direction uses natural language explanations (NLEs), often with the goal of improving model interpretability (Zhou et al., 2020; Wiegreffe and Marasovi´c, 2021, inter alia ).”
Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them (2022, methodology): “For example, providing reasoning paths after the answer has been used to improve model explainability (Zhou et al., 2020; Stacey et al., 2021; Marasović et al., 2022; Mishra et al., 2022; Hase and Bansal, 2022; Wiegreffe et al., 2022; Lampinen et al., 2022).”
Can language models learn from explanations in context? (2022, methodology): “…explored training or tuning of language processing models with task instructions (e.g. Raffel et al., 2020; Wei et al., 2021; Ouyang et al., 2022; Sanh et al., 2021), and with explanations (Cam-buru et al., 2018; Rajani et al., 2019; Narang et al., 2020; Zhou et al., 2020; Hase and Bansal, 2021).”
STaR: Bootstrapping Reasoning With Reasoning (2022, background): “In addition, works have aimed to explain why rationales help: some have analyzed their impact from the perspective of latent variable models [19] while others have provided formal proofs of the benefit of intermediate task supervision [20].”
When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data (2021, methodology): “…2020), as additional supervision (Narang et al., 2020; Hase et al., 2020; Pruthi et al., 2020) or intermediate structured variables (Camburu et al., 2018; Rajani et al., 2019; Wiegreffe et al., 2020), and simply as model inputs (Rupprecht et al., 2018; Co-Reyes et al., 2019; Zhou et al., 2020).”
Decomposition Enhances Reasoning via Self-Evaluation Guided Decoding (2023, unknown): “One approach is to generate rationales to enhance model interpretability (Zhou et al., 2020; Wiegreffe and Marasović, 2021; Wiegreffe et al., 2021).”