NLP Interpretability aims to increase trust in model predictions. This makes evaluating interpretability approaches a pressing issue. There are multiple datasets for evaluating NLP Interpretability, but their dependence on human provided ground truths raises questions about their unbiasedness. In this work, we take a different approach and formulate a specific classification task by diverting question-answering datasets. For this custom classification task, the interpretability ground-truth arises directly from the definition of the classification problem. We use this method to propose a benchmark and lay the groundwork for future research in NLP interpretability by evaluating a wide range of current state of the art methods.
This paper proposes a set of criteria to evaluate the objectiveness of explanation methods of neural networks, which is crucial for the development of explainable AI, but it also presents significant challenges. The core challenge is that people usually cannot obtain ground-truth explanations of the neural network. To this end, we design four metrics to evaluate explanation results without ground-truth explanations. Our metrics can be broadly applied to nine benchmark methods of interpreting neural networks, which provides new insights of explanation methods.
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of Washington（华盛顿大学）
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 class…
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）
This paper introduces our systems for the first two subtasks of SemEval Task4: Commonsense Validation and Explanation. To clarify the intention for judgment and inject contrastive information for selection, we propose the input reconstruction strategy with prompt templates. Specifically, we formalize the subtasks into the multiple-choice question answering format and construct the input with the prompt templates, then, the final prediction of question answering is considered as the result of subtasks. Experimental results show that our approaches achieve significant performance compared with t…
Can Modern NLP Systems Reliably Annotate Chest Radiography Exams? A Pre-Purchase Evaluation and Comparative Study of Solutions from AWS, Google, Azure, John Snow Labs, and Open-Source Models on an Independent Pediatric Dataset
EPFL（洛桑联邦理工学院）；AXA（安盛集团）；Inria（法国国家信息与自动化研究所）；Sorbonne Université（索邦大学）；Polish Academy of Science（波兰科学院）
Current methods for Black-Box NLP interpretability, like LIME or SHAP, are based on altering the text to interpret by removing words and modeling the Black-Box response. In this paper, we outline limitations of this approach when using complex BERT-based classifiers: The word-based sampling produces texts that are out-of-distribution for the classifier and further gives rise to a high-dimensional search space, which can't be sufficiently explored when time or computation power is limited. Both of these challenges can be addressed by using segments as elementary building blocks for NLP interpre…
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））
Recently, state-of-the-art NLP models gained an increasing syntactic and semantic understanding of language, and explanation methods are crucial to understand their decisions. Occlusion is a well established method that provides explanations on discrete language data, e.g. by removing a language unit from an input and measuring the impact on a model's decision. We argue that current occlusion-based methods often produce invalid or syntactically incorrect language data, neglecting the improved abilities of recent NLP models. Furthermore, gradient-based explanation methods disregard the discrete…
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；Oldenburg University（奥尔登堡大学）
Training a model with access to human explanations can improve data efficiency and model performance on in- and out-of-domain data. Adding to these empirical findings, similarity with the process of human learning makes learning from explanations a promising way to establish a fruitful human-machine interaction. Several methods have been proposed for improving natural language processing (NLP) models with human explanations, that rely on different explanation types and mechanism for integrating these explanations into the learning process. These methods are rarely compared with each other, mak…
Center for Information and Language Processing（信息与语言处理中心）；LMU Munich（慕尼黑大学）
The behavior of deep neural networks (DNNs) is hard to understand. This makes it necessary to explore post hoc explanation methods. We conduct the first comprehensive evaluation of explanation methods for NLP. To this end, we design two novel evaluation paradigms that cover two important classes of NLP problems: small context and large context problems. Both paradigms require no manual annotation and are therefore broadly applicable. We also introduce LIMSSE, an explanation method inspired by LIME that is designed for NLP. We show empirically that LIMSSE, LRP and DeepLIFT are the most effectiv…
Ground Truth Generation for Multilingual Historical NLP using LLMs
ARTFL Project, Romance Languages and Literatures, University of Chicago（ARTFL项目， Romance语言与文学系，芝加哥大学）；Department of History, University of Chicago（历史系，芝加哥大学）；Libraries and School of Information Studies, Purdue University（图书馆与信息科学学院，普渡大学）
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；IBM Research（IBM研究院）
Explanation methods have emerged as an important tool to highlight the features responsible for the predictions of neural networks. There is mounting evidence that many explanation methods are rather unreliable and susceptible to malicious manipulations. In this paper, we particularly aim to understand the robustness of explanation methods in the context of text modality. We provide initial insights and results towards devising a successful adversarial attack against text explanations. To our knowledge, this is the first attempt to evaluate the adversarial robustness of an explanation method. …
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））
In the language domain, as in other domains, neural explainability takes an ever more important role, with feature attribution methods on the forefront. Many such methods require considerable computational resources and expert knowledge about implementation details and parameter choices. To facilitate research, we present Thermostat which consists of a large collection of model explanations and accompanying analysis tools. Thermostat allows easy access to over 200k explanations for the decisions of prominent state-of-the-art models spanning across different NLP tasks, generated with multiple e…
University of Southern California（南加州大学）；Sony Group Corporation（索尼集团公司）
NLP models are susceptible to learning spurious biases (i.e., bugs) that work on some datasets but do not properly reflect the underlying task. Explanation-based model debugging aims to resolve spurious biases by showing human users explanations of model behavior, asking users to give feedback on the behavior, then using the feedback to update the model. While existing model debugging methods have shown promise, their prototype-level implementations provide limited practical utility. Thus, we propose XMD: the first open-source, end-to-end framework for explanation-based model debugging. Given …
University of Oxford（牛津大学）；University of Warmia and Mazury in Olsztyn（奥尔什丁瓦尔米亚-马祖里大学）；Royal Holloway, University of London（伦敦大学皇家霍洛威学院）
We build on abduction-based explanations for ma-chine learning and develop a method for computing local explanations for neural network models in natural language processing (NLP). Our explanations comprise a subset of the words of the in-put text that satisfies two key features: optimality w.r.t. a user-defined cost function, such as the length of explanation, and robustness, in that they ensure prediction invariance for any bounded perturbation in the embedding space of the left out words. We present two solution algorithms, respectively based on implicit hitting sets and maximum universal s…
Debugging a machine learning model is hard since the bug usually involves the training data and the learning process. This becomes even harder for an opaque deep learning model if we have no clue about how the model actually works. In this survey, we review papers that exploit explanations to enable humans to give feedback and debug NLP models. We call this problem explanation-based human debugging (EBHD). In particular, we categorize and discuss existing work along three dimensions of EBHD (the bug context, the workflow, and the experimental setting), compile findings on how EBHD components a…
As the applications of Natural Language Processing (NLP) in sensitive areas like Political Profiling, Review of Essays in Education, etc. proliferate, there is a great need for increasing transparency in NLP models to build trust with stakeholders and identify biases. A lot of work in Explainable AI has aimed to devise explanation methods that give humans insights into the workings and predictions of NLP models. While these methods distill predictions from complex models like Neural Networks into consumable explanations, how humans understand these explanations is still widely unexplored. Inna…
CHiRPE: A Step Towards Real-World Clinical NLP with Clinician-Oriented Model Explanations
Orygen and The University of Melbourne（Orygen和墨尔本大学）；AIM for Health Lab, Monash University（AIM for Health实验室，墨尔本大学）；University of Liverpool（利物浦大学）；Yale School of Medicine, Yale University（耶鲁医学院，耶鲁大学）；Brigham and Women’s Hospital, Harvard Medical School（哈佛医学院布里奇沃特医院）
Wayfair（Wayfair公司）；Sogou Inc（搜狗公司）；MIT-IBM Watson AI Lab（麻省理工-IBM沃森人工智能实验室）；IBM Research（IBM研究院）；IBM Data and AI（IBM数据与人工智能部门）
In the recent advances of natural language processing, the scale of the state-of-the-art models and datasets is usually extensive, which challenges the application of sample-based explanation methods in many aspects, such as explanation interpretability, efficiency, and faithfulness. In this work, for the first time, we can improve the interpretability of explanations by allowing arbitrary text sequences as the explanation unit. On top of this, we implement a hessian-free method with a model faithfulness guarantee. Finally, to compare our method with the others, we propose a semantic-based eva…
Peking University（北京大学）；Harbin Institute of Technology（哈尔滨工业大学）；University of California, Santa Barbara（加州大学圣巴巴拉分校）
Building explainable systems is a critical problem in the field of Natural Language Processing (NLP), since most machine learning models provide no explanations for the predictions. Existing approaches for explainable machine learning systems tend to focus on interpreting the outputs or the connections between inputs and outputs. However, the fine-grained information is often ignored, and the systems do not explicitly generate the human-readable explanations. To better alleviate this problem, we propose a novel generative explanation framework that learns to make classification decisions and g…
A growing effort in NLP aims to build datasets of human explanations. However, the term explanation encompasses a broad range of notions, each with different properties and ramifications. Our goal is to provide an overview of diverse types of explanations and human limitations, and discuss implications for collecting and using explanations in NLP. Inspired by prior work in psychology and cognitive sciences, we group existing human explanations in NLP into three categories: proximal mechanism, evidence, and procedure. These three types differ in nature and have implications for the resultant ex…
A key aim of science is explanation, yet the idea of explaining language phenomena has taken a backseat in mainstream Natural Language Processing (NLP) and many other areas of Artificial Intelligence. I argue that explanation of linguistic behaviour should be a main goal of NLP, and that this is not the same as making NLP models explainable. To illustrate these ideas, some recent models of human language production are compared with each other. I conclude by asking what it would mean for NLP research and institutional policies if our community took explanatory value seriously, while heeding so…
University of Hamburg（汉堡大学）；University of Copenhagen（哥本哈根大学）
Natural language explanations promise to offer intuitively understandable explanations of a neural network's decision process in complex vision-language tasks, as pursued in recent VL-NLE models. While current models offer impressive performance on task accuracy and explanation plausibility, they suffer from a range of issues: Some models feature a modular design where the explanation generation module is poorly integrated with a separate module for task-answer prediction, employ backbone models trained on limited sets of tasks, or incorporate ad hoc solutions to increase performance on single…
Technion – Israel Institute of Technology（以色列理工学院）；Stanford University（斯坦福大学）；Ghent University（根特大学）
The increasing size and complexity of modern ML systems has improved their predictive capabilities but made their behavior harder to explain. Many techniques for model explanation have been developed in response, but we lack clear criteria for assessing these techniques. In this paper, we cast model explanation as the causal inference problem of estimating causal effects of real-world concepts on the output behavior of ML models given actual input data. We introduce CEBaB, a new benchmark dataset for assessing concept-based explanation methods in Natural Language Processing (NLP). CEBaB consis…
Shapley Values, a solution to the credit assignment problem in cooperative game theory, are a popular type of explanation in machine learning, having been used to explain the importance of features, embeddings, and even neurons. In NLP, however, leave-one-out and attention-based explanations still predominate. Can we draw a connection between these different methods? We formally prove that -- save for the degenerate case -- attention weights and leave-one-out values cannot be Shapley Values. $\textit{Attention flow}$ is a post-processed variant of attention weights obtained by running the max-…
Explanation methods in Interpretable NLP often explain the model's decision by extracting evidence (rationale) from the input texts supporting the decision. Benchmark datasets for rationales have been released to evaluate how good the rationale is. The ground truth rationales in these datasets are often human annotations obtained via crowd-sourced websites. Valuable as these datasets are, the details on how those human annotations are obtained are often not clearly specified. We conduct comprehensive controlled experiments using crowd-sourced websites on two widely used datasets in Interpretab…
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；Technische Universität Berlin（柏林工业大学）
The human-centric explainable artificial intelligence (HCXAI) community has raised the need for framing the explanation process as a conversation between human and machine. In this position paper, we establish desiderata for Mediators, text-based conversational agents which are capable of explaining the behavior of neural models interactively using natural language. From the perspective of natural language processing (NLP) research, we engineer a blueprint of such a Mediator for the task of sentiment analysis and assess how far along current research is on the path towards dialogue-based expla…
Faculty of Electrical Engineering and Computing, University of Zagreb（萨格勒布大学电气工程与计算学院）
The attention mechanism has quickly become ubiquitous in NLP. In addition to improving performance of models, attention has been widely used as a glimpse into the inner workings of NLP models. The latter aspect has in the recent years become a common topic of discussion, most notably in work of Jain and Wallace, 2019; Wiegreffe and Pinter, 2019. With the shortcomings of using attention weights as a tool of transparency revealed, the attention mechanism has been stuck in a limbo without concrete proof when and whether it can be used as an explanation. In this paper, we provide an explanation as…
Who's Laughing Now? An Overview of Computational Humour Generation and Explanation
Department of Computer Science, The University of Sheffield, UK（谢菲尔德大学计算机科学系）；Department of Computer Science, The University of Manchester, UK（曼彻斯特大学计算机科学系）
Tsinghua University（清华大学）；University of Southern California（南加利福尼亚大学）；Snap Research（Snap研究院）
While deep neural networks have achieved impressive performance on a range of NLP tasks, these data-hungry models heavily rely on labeled data, which restricts their applications in scenarios where data annotation is expensive. Natural language (NL) explanations have been demonstrated very useful additional supervision, which can provide sufficient domain knowledge for generating more labeled data over new instances, while the annotation time only doubles. However, directly applying them for augmenting model learning encounters two challenges: (1) NL explanations are unstructured and inherentl…
Attention mechanisms have seen wide adoption in neural NLP models. In addition to improving predictive performance, these are often touted as affording transparency: models equipped with attention provide a distribution over attended-to input units, and this is often presented (at least implicitly) as communicating the relative importance of inputs. However, it is unclear what relationship exists between attention weights and model outputs. In this work, we perform extensive experiments across a variety of NLP tasks that aim to assess the degree to which attention weights provide meaningful `e…
Is Explanation the Cure? Misinformation Mitigation in the Short Term and Long Term
Institute of Information Science, Academia Sinica（中央研究院资讯科学研究所）；Department of Computer Science, National Tsing Hua University（国立清华大学资讯工程学系）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；The Pennsylvania State University（宾夕法尼亚州立大学）
Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study
Technical University of Munich, School of Computation, Information and Technology, Department of Computer Science, Munich, Germany（慕尼黑技术大学，计算、信息与技术学院，计算机科学系，德国慕尼黑）
Digital Reasoning / Smarsh, Inc（Digital Reasoning / Smarsh公司）
The healthcare domain is one of the most exciting application areas for machine learning, but a lack of model transparency contributes to a lag in adoption within the industry. In this work, we explore the current art of explainability and interpretability within a case study in clinical text classification, using a task of mortality prediction within MIMIC-III clinical notes. We demonstrate various visualization techniques for fully interpretable methods as well as model-agnostic post hoc attributions, and we provide a generalized method for evaluating the quality of explanations using infide…
An increasing number of machine learning models have been deployed in domains with high stakes such as finance and healthcare. Despite their superior performances, many models are black boxes in nature which are hard to explain. There are growing efforts for researchers to develop methods to interpret these black-box models. Post hoc explanations based on perturbations, such as LIME, are widely used approaches to interpret a machine learning model after it has been built. This class of methods has been shown to exhibit large instability, posing serious challenges to the effectiveness of the me…
University of Amsterdam（阿姆斯特丹大学）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）
There has been significant debate in the NLP community about whether or not attention weights can be used as an explanation - a mechanism for interpreting how important each input token is for a particular prediction. The validity of "attention as explanation" has so far been evaluated by computing the rank correlation between attention-based explanations and existing feature attribution explanations using LSTM-based models. In our work, we (i) compare the rank correlation between five more recent feature attribution methods and two attention-based methods, on two types of NLP tasks, and (ii) …
Interpretable AI for Time-Series: Multi-Model Heatmap Fusion with Global Attention and NLP-Generated Explanations
Department of Electrical and Computer Engineering, Iowa State University, Ames, 50011 IA USA（电气与计算机工程系，爱荷华州立大学）；Department of Agricultural Biosystem Engineering, Iowa State University, Ames,IA 50011 USA（农业生物系统工程系，爱荷华州立大学）
University of Tübingen（蒂宾根大学）；MPI for Informatics（马克斯·普朗克信息学研究所）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
Providing explanations in the context of Visual Question Answering (VQA) presents a fundamental problem in machine learning. To obtain detailed insights into the process of generating natural language explanations for VQA, we introduce the large-scale CLEVR-X dataset that extends the CLEVR dataset with natural language explanations. For each image-question pair in the CLEVR dataset, CLEVR-X contains multiple structured textual explanations which are derived from the original scene graphs. By construction, the CLEVR-X explanations are correct and describe the reasoning and visual information th…
Indian Institute of Science（印度科学研究所）；Google（谷歌）；Google Assistant（谷歌助手）；Google Research（谷歌研究院）
The attention layer in a neural network model provides insights into the model's reasoning behind its prediction, which are usually criticized for being opaque. Recently, seemingly contradictory viewpoints have emerged about the interpretability of attention weights (Jain & Wallace, 2019; Vig & Belinkov, 2019). Amid such confusion arises the need to understand attention mechanism more systematically. In this work, we attempt to fill this gap by giving a comprehensive explanation which justifies both kinds of observations (i.e., when is attention interpretable and when it is not). Through a ser…
Freie Universität Berlin（柏林自由大学）；University of Southern Denmark（南丹麦大学）；Universität der Bundeswehr München（慕尼黑联邦国防军大学）
Hate speech detection is a common downstream application of natural language processing (NLP) in the real world. In spite of the increasing accuracy, current data-driven approaches could easily learn biases from the imbalanced data distributions originating from humans. The deployment of biased models could further enhance the existing social biases. But unlike handling tabular data, defining and mitigating biases in text classifiers, which deal with unstructured data, are more challenging. A popular solution for improving machine learning fairness in NLP is to conduct the debiasing process wi…
