Humans have been shown to give contrastive explanations, which explain why an observed event happened rather than some other counterfactual event (the contrast case).Despite the influential role that contrastivity plays in how humans explain, this property is largely missing from current methods for explaining NLP models. We present MIN-IMAL CONTRASTIVE EDITING (MICE), a method for producing contrastive explanations of model predictions in the form of edits to inputs that change model outputs to the contrast case. Our experiments across three tasks-binary sentiment classification, topic classification, and multiple-choice question answering-show that MICE is able to produce edits that are not only contrastive, but also minimal and fluent, consistent with human contrastive edits. We demonstrate how MICE edits can be used for two use cases in NLP system development-debugging incorrect model outputs and uncovering dataset artifacts-and thereby illustrate that producing contrastive explanations is a promising research direction for model interpretability.
Generating text from structured inputs, such as meaning representations or RDF triples, has often involved the use of specialized graphencoding neural networks. However, recent applications of pretrained transformers to linearizations of graph inputs have yielded stateof-the-art generation results on graph-to-text tasks. Here, we explore the ability of these linearized models to encode local graph structures, in particular their invariance to the graph linearization strategy and their ability to reconstruct corrupted inputs. Our findings motivate solutions to enrich the quality of models' implicit graph encodings via scaffolding. Namely, we use graph-denoising objectives implemented in a multi-task text-to-text framework. We find that these denoising scaffolds lead to substantial improvements in downstream generation in low-resource settings.
An attention matrix of a transformer selfattention sublayer can provably be decomposed into two components and only one of them (effective attention) contributes to the model output. This leads us to ask whether visualizing effective attention gives different conclusions than interpretation of standard attention. Using a subset of the GLUE tasks and BERT, we carry out an analysis to compare the two attention matrices, and show that their interpretations differ. Effective attention is less associated with the features related to the language modeling pretraining such as the separator token, and it has more potential to illustrate linguistic features captured by the model for solving the end-task. Given the found differences, we recommend using effective attention for studying a transformer's behavior since it is more pertinent to the model output by design.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.