scispace - formally typeset
Open accessPosted Content

Contrastive Explanations for Model Interpretability

Abstract: Contrastive explanations clarify why an event occurred in contrast to another. They are more inherently intuitive to humans to both produce and comprehend. We propose a methodology to produce contrastive explanations for classification models by modifying the representation to disregard non-contrastive information, and modifying model behavior to only be based on contrastive reasoning. Our method is based on projecting model representation to a latent space that captures only the features that are useful (to the model) to differentiate two potential decisions. We demonstrate the value of contrastive explanations by analyzing two different scenarios, using both high-level abstract concept attribution and low-level input token/span attribution, on two widely used text classification tasks. Specifically, we produce explanations for answering: for which label, and against which alternative label, is some aspect of the input useful? And which aspects of the input are useful for and against particular decisions? Overall, our findings shed light on the ability of label-contrastive explanations to provide a more accurate and finer-grained interpretability of a model's decision.

... read more

Topics: Interpretability (53%)
Citations
  More

11 results found


Open accessPosted Content
Abstract: 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 Minimal 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.

... read more

26 Citations


Open accessProceedings ArticleDOI: 10.18653/V1/2021.FINDINGS-ACL.336
01 Aug 2021-

6 Citations


Open accessPosted Content
25 Mar 2021-arXiv: Learning
Abstract: Counterfactual examples identify how inputs can be altered to change the predicted class of a classifier, thus opening up the black-box nature of, e.g., deep neural networks. We propose a method, ECINN, that utilizes the generative capacities of invertible neural networks for image classification to generate counterfactual examples efficiently. In contrast to competing methods that sometimes need a thousand evaluations or more of the classifier, ECINN has a closed-form expression and generates a counterfactual in the time of only two evaluations. Arguably, the main challenge of generating counterfactual examples is to alter only input features that affect the predicted outcome, i.e., class-dependent features. Our experiments demonstrate how ECINN alters class-dependent image regions to change the perceptual and predicted class of the counterfactuals. Additionally, we extend ECINN to also produce heatmaps (ECINNh) for easy inspection of, e.g., pairwise class-dependent changes in the generated counterfactual examples. Experimentally, we find that ECINNh outperforms established methods that generate heatmap-based explanations.

... read more

3 Citations


Open accessPosted Content
Abstract: When language models process syntactically complex sentences, do they use their representations of syntax in a manner that is consistent with the grammar of the language? We propose AlterRep, an intervention-based method to address this question. For any linguistic feature of a given sentence, AlterRep generates counterfactual representations by altering how the feature is encoded, while leaving intact all other aspects of the original representation. By measuring the change in a model's word prediction behavior when these counterfactual representations are substituted for the original ones, we can draw conclusions about the causal effect of the linguistic feature in question on the model's behavior. We apply this method to study how BERT models of different sizes process relative clauses (RCs). We find that BERT variants use RC boundary information during word prediction in a manner that is consistent with the rules of English grammar; this RC boundary information generalizes to a considerable extent across different RC types, suggesting that BERT represents RCs as an abstract linguistic category.

... read more

Topics: Syntax (55%), Sentence (54%), Grammar (53%) ... read more

1 Citations


Open accessPosted Content
Abstract: Neural network models have achieved state-of-the-art performances in a wide range of natural language processing (NLP) tasks. However, a long-standing criticism against neural network models is the lack of interpretability, which not only reduces the reliability of neural NLP systems but also limits the scope of their applications in areas where interpretability is essential (e.g., health care applications). In response, the increasing interest in interpreting neural NLP models has spurred a diverse array of interpretation methods over recent years. In this survey, we provide a comprehensive review of various interpretation methods for neural models in NLP. We first stretch out a high-level taxonomy for interpretation methods in NLP, i.e., training-based approaches, test-based approaches, and hybrid approaches. Next, we describe sub-categories in each category in detail, e.g., influence-function based methods, KNN-based methods, attention-based models, saliency-based methods, perturbation-based methods, etc. We point out deficiencies of current methods and suggest some avenues for future research.

... read more

Topics: Interpretability (55%), Deep learning (55%)

1 Citations


References
  More

49 results found


Open accessPosted Content
Abstract: Language model pretraining has led to significant performance gains but careful comparison between different approaches is challenging. Training is computationally expensive, often done on private datasets of different sizes, and, as we will show, hyperparameter choices have significant impact on the final results. We present a replication study of BERT pretraining (Devlin et al., 2019) that carefully measures the impact of many key hyperparameters and training data size. We find that BERT was significantly undertrained, and can match or exceed the performance of every model published after it. Our best model achieves state-of-the-art results on GLUE, RACE and SQuAD. These results highlight the importance of previously overlooked design choices, and raise questions about the source of recently reported improvements. We release our models and code.

... read more

6,623 Citations


Proceedings ArticleDOI: 10.1145/2939672.2939778
13 Aug 2016-
Abstract: Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one. In this work, we propose LIME, a novel explanation technique that explains the predictions of any classifier in an interpretable and faithful manner, by learning an interpretable model locally varound the prediction. We also propose a method to explain models by presenting representative individual predictions and their explanations in a non-redundant way, framing the task as a submodular optimization problem. We demonstrate the flexibility of these methods by explaining different models for text (e.g. random forests) and image classification (e.g. neural networks). We show the utility of explanations via novel experiments, both simulated and with human subjects, on various scenarios that require trust: deciding if one should trust a prediction, choosing between models, improving an untrustworthy classifier, and identifying why a classifier should not be trusted.

... read more

6,284 Citations


Open accessProceedings Article
23 Dec 2013-
Abstract: This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets). We consider two visualisation techniques, based on computing the gradient of the class score with respect to the input image. The first one generates an image, which maximises the class score [5], thus visualising the notion of the class, captured by a ConvNet. The second technique computes a class saliency map, specific to a given image and class. We show that such maps can be employed for weakly supervised object segmentation using classification ConvNets. Finally, we establish the connection between the gradient-based ConvNet visualisation methods and deconvolutional networks [13].

... read more

3,612 Citations


Open accessProceedings ArticleDOI: 10.18653/V1/D15-1075
21 Aug 2015-
Abstract: Understanding entailment and contradiction is fundamental to understanding natural language, and inference about entailment and contradiction is a valuable testing ground for the development of semantic representations. However, machine learning research in this area has been dramatically limited by the lack of large-scale resources. To address this, we introduce the Stanford Natural Language Inference corpus, a new, freely available collection of labeled sentence pairs, written by humans doing a novel grounded task based on image captioning. At 570K pairs, it is two orders of magnitude larger than all other resources of its type. This increase in scale allows lexicalized classifiers to outperform some sophisticated existing entailment models, and it allows a neural network-based model to perform competitively on natural language inference benchmarks for the first time.

... read more

Topics: Textual entailment (65%), Inference (58%), Natural language (56%)

2,015 Citations


Open accessProceedings ArticleDOI: 10.18653/V1/N18-1101
01 Jun 2018-
Abstract: This paper introduces the Multi-Genre Natural Language Inference (MultiNLI) corpus, a dataset designed for use in the development and evaluation of machine learning models for sentence understanding. At 433k examples, this resource is one of the largest corpora available for natural language inference (a.k.a. recognizing textual entailment), improving upon available resources in both its coverage and difficulty. MultiNLI accomplishes this by offering data from ten distinct genres of written and spoken English, making it possible to evaluate systems on nearly the full complexity of the language, while supplying an explicit setting for evaluating cross-genre domain adaptation. In addition, an evaluation using existing machine learning models designed for the Stanford NLI corpus shows that it represents a substantially more difficult task than does that corpus, despite the two showing similar levels of inter-annotator agreement.

... read more

Topics: Textual entailment (57%), Inference (55%), Sentence (54%)

1,786 Citations


Performance
Metrics
No. of citations received by the Paper in previous years
YearCitations
20221
20219
20201
Network Information
Related Papers (5)