LIREx: Augmenting Language Inference with Relevant Explanation

By Xinyan Zhao, V. G. Vinod Vydiswaran. 2020

41 citations recorded by the source corpus.

Natural language explanations (NLEs) are a special form of data annotation in which annotators identify rationales (most significant text tokens) when assigning labels to data instances, and write out explanations for the labels in natural language based on the rationales. NLEs have been shown to capture human reasoning better, but not as beneficial for natural language inference (NLI). In this paper, we analyze two primary flaws in the way NLEs are currently used to train explanation generators for language inference tasks. We find that the explanation generators do not take into account the variability inherent in human explanation of labels, and that the current explanation generation models generate spurious explanations. To overcome these limitations, we propose a novel framework, LIREx, that incorporates both a rationale-enabled explanation generator and an instance selector to select only relevant, plausible NLEs to augment NLI models. When evaluated on the standardized SNLI data set, LIREx achieved an accuracy of 91.87%, an improvement of 0.32 over the baseline and matching the best-reported performance on the data set. It also achieves significantly better performance than previous studies when transferred to the out-of-domain MultiNLI data set. Qualitative analysis shows that LIREx generates flexible, faithful, and relevant NLEs that allow the model to be more robust to spurious explanations. The code is available at https://github.com/zhaoxy92/LIREx.

Subfields: Artificial Intelligence, Natural Language Processing, Safety, Robustness & Interpretability

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

In Safety, Robustness & Interpretability

Citations in the corpus

Natural Language Inference with a Human Touch: Using Human Explanations to Guide Model Attention (2021, methodology): “While LIREx (Zhao and Vydiswaran, 2020) found a significant improvement from using e-SNLI, this was not the case for the other methods displayed: e-SNLI (Camburu et al.”
Supervising Model Attention with Human Explanations for Robust Natural Language Inference (2021, methodology): “Zhao and Vydiswaran (2021) also generate explanations for each class, ﬁrst predicting which of the words in a hypothesis are relevant given the class, training with the highlighted words in e-SNLI.”