The Role of Interactive Visualization in Explaining (Large) NLP Models: from Data to Inference
Uncharted Software Inc（未知软件公司）；University of Konstanz（康斯坦茨大学）；University of Stuttgart（斯图加特大学）；University of Maryland, BC（马里兰大学巴尔的摩县分校）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；IBM Research Cambridge（IBM剑桥研究院）
Richard Brath, Daniel Keim, Johannes Knittel, Shimei Pan, Pia Sommerauer, Hendrik Strobelt
With a constant increase of learned parameters, modern neural language models become increasingly more powerful. Yet, explaining these complex model's behavior remains a widely unsolved problem. In this paper, we discuss the role interactive visualization can play in explaining NLP models (XNLP). We motivate the use of visualization in relation to target users and common NLP pipelines. We also present several use cases to provide concrete examples on XNLP with visualization. Finally, we point out an extensive list of research opportunities in this field.
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…
Zhejiang University（浙江大学）；Computer Center of Peking University（北京大学计算中心）；Peng Cheng Laboratory（鹏城实验室）
Existing approaches to explaining deep learning models in NLP usually suffer from two major drawbacks: (1) the main model and the explaining model are decoupled: an additional probing or surrogate model is used to interpret an existing model, and thus existing explaining tools are not self-explainable; (2) the probing model is only able to explain a model's predictions by operating on low-level features by computing saliency scores for individual words but are clumsy at high-level text units such as phrases, sentences, or paragraphs. To deal with these two issues, in this paper, we propose a s…
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…
While state-of-the-art NLP explainability (XAI) methods focus on explaining per-sample decisions in supervised end or probing tasks, this is insufficient to explain and quantify model knowledge transfer during (un-)supervised training. Thus, for TX-Ray, we modify the established computer vision explainability principle of 'visualizing preferred inputs of neurons' to make it usable transfer analysis and NLP. This allows one to analyze, track and quantify how self- or supervised NLP models first build knowledge abstractions in pretraining (1), and then transfer these abstractions to a new domain…
We present the Language Interpretability Tool (LIT), an open-source platform for visualization and understanding of NLP models. We focus on core questions about model behavior: Why did my model make this prediction? When does it perform poorly? What happens under a controlled change in the input? LIT integrates local explanations, aggregate analysis, and counterfactual generation into a streamlined, browser-based interface to enable rapid exploration and error analysis. We include case studies for a diverse set of workflows, including exploring counterfactuals for sentiment analysis, measuring…
Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；Technische Universität Berlin（柏林工业大学）；Korea University（高丽大学）
Layer-wise relevance propagation (LRP) is a recently proposed technique for explaining predictions of complex non-linear classifiers in terms of input variables. In this paper, we apply LRP for the first time to natural language processing (NLP). More precisely, we use it to explain the predictions of a convolutional neural network (CNN) trained on a topic categorization task. Our analysis highlights which words are relevant for a specific prediction of the CNN. We compare our technique to standard sensitivity analysis, both qualitatively and quantitatively, using a "word deleting" perturbatio…
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of California, Irvine（加州大学欧文分校）
Neural NLP models are increasingly accurate but are imperfect and opaque---they break in counterintuitive ways and leave end users puzzled at their behavior. Model interpretation methods ameliorate this opacity by providing explanations for specific model predictions. Unfortunately, existing interpretation codebases make it difficult to apply these methods to new models and tasks, which hinders adoption for practitioners and burdens interpretability researchers. We introduce AllenNLP Interpret, a flexible framework for interpreting NLP models. The toolkit provides interpretation primitives (e.…
As part of the NLP Scholar project, we created a single unified dataset of NLP papers and their meta-information (including citation numbers), by extracting and aligning information from the ACL Anthology and Google Scholar. In this paper, we describe several interconnected interactive visualizations (dashboards) that present various aspects of the data. Clicking on an item within a visualization or entering query terms in the search boxes filters the data in all visualizations in the dashboard. This allows users to search for papers in the area of their interest, published within specific tim…
Carnegie Mellon University（卡内基梅隆大学）；Petuum Inc.（Petuum公司）；Sun Yat-sen University（中山大学）；UC San Diego（加州大学圣迭戈分校）
Empirical natural language processing (NLP) systems in application domains (e.g., healthcare, finance, education) involve interoperation among multiple components, ranging from data ingestion, human annotation, to text retrieval, analysis, generation, and visualization. We establish a unified open-source framework to support fast development of such sophisticated NLP workflows in a composable manner. The framework introduces a uniform data representation to encode heterogeneous results by a wide range of NLP tasks. It offers a large repository of processors for NLP tasks, visualization, and an…
Robust visualization of complex data is critical for the effective use of NLP for event classification, as the volume of data is large and the high-dimensional structure of text makes data challenging to summarize succinctly. In event extraction tasks in particular, visualization can aid in understanding and illustrating the textual relationships from which machine learning tools produce insights. Through our case study which seeks to identify potential triggers of state-led mass killings from news articles using NLP, we demonstrate how visualizations can aid in each stage, from exploratory an…
Zhejiang University（浙江大学）；Hong Kong University of Science and Technology（香港科技大学）；MIT Media Lab（麻省理工学院媒体实验室）；Southern University of Science and Technology（南方科技大学）
Natural language interfaces (NLIs) enable users to flexibly specify analytical intentions in data visualization. However, diagnosing the visualization results without understanding the underlying generation process is challenging. Our research explores how to provide explanations for NLIs to help users locate the problems and further revise the queries. We present XNLI, an explainable NLI system for visual data analysis. The system introduces a Provenance Generator to reveal the detailed process of visual transformations, a suite of interactive widgets to support error adjustments, and a Hint …
Modul University Vienna（维也纳模都尔大学）；Modul Technology GmbH（模都尔科技有限责任公司）；Central Washington University（中央华盛顿大学）；Transilvania University（特兰西瓦尼亚大学）
During the last decade, Natural Language Processing has become, after Computer Vision, the second field of Artificial Intelligence that was massively changed by the advent of Deep Learning. Regardless of the architecture, the language models of the day need to be able to process or generate text, as well as predict missing words, sentences or relations depending on the task. Due to their black-box nature, such models are difficult to interpret and explain to third parties. Visualization is often the bridge that language model designers use to explain their work, as the coloring of the salient …
Deep neural networks are increasingly used in natural language processing (NLP) models. However, the need to interpret and explain the results from complex algorithms are limiting their widespread adoption in regulated industries such as banking. There has been recent work on interpretability of machine learning algorithms with structured data. But there are only limited techniques for NLP applications where the problem is more challenging due to the size of the vocabulary, high-dimensional nature, and the need to consider textual coherence and language structure. This paper develops a methodo…
Central Washington University（中央华盛顿大学）；University of Ottawa（渥太华大学）；Transilvania University（特兰西瓦尼亚大学）
The introduction of Transformer neural networks has changed the landscape of Natural Language Processing (NLP) during the last years. So far, none of the visualization systems has yet managed to examine all the facets of the Transformers. This gave us the motivation of the current work. We propose a new NLP Transformer context-sensitive visualization method that leverages existing NLP tools to find the most significant groups of tokens (words) that have the greatest effect on the output, thus preserving some context from the original text. First, we use a sentence-level dependency parser to hi…
Why do large pre-trained transformer-based models perform so well across a wide variety of NLP tasks? Recent research suggests the key may lie in multi-headed attention mechanism's ability to learn and represent linguistic information. Understanding how these models represent both syntactic and semantic knowledge is vital to investigate why they succeed and fail, what they have learned, and how they can improve. We present Dodrio, an open-source interactive visualization tool to help NLP researchers and practitioners analyze attention mechanisms in transformer-based models with linguistic know…
Modern deep learning models for NLP are notoriously opaque. This has motivated the development of methods for interpreting such models, e.g., via gradient-based saliency maps or the visualization of attention weights. Such approaches aim to provide explanations for a particular model prediction by highlighting important words in the corresponding input text. While this might be useful for tasks where decisions are explicitly influenced by individual tokens in the input, we suspect that such highlighting is not suitable for tasks where model decisions should be driven by more complex reasoning.…
Beuth University of Applied Sciences Berlin（柏林贝uth应用科学大学）
Explainability and interpretability are two important concepts, the absence of which can and should impede the application of well-performing neural networks to real-world problems. At the same time, they are difficult to incorporate into the large, black-box models that achieve state-of-the-art results in a multitude of NLP tasks. Bidirectional Encoder Representations from Transformers (BERT) is one such black-box model. It has become a staple architecture to solve many different NLP tasks and has inspired a number of related Transformer models. Understanding how these models draw conclusions…
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…
While there has been a recent explosion of work on ExplainableAI ExAI on deep models that operate on imagery and tabular data, textual datasets present new challenges to the ExAI community. Such challenges can be attributed to the lack of input structure in textual data, the use of word embeddings that add to the opacity of the models and the difficulty of the visualization of the inner workings of deep models when they are trained on textual data. Lately, methods have been developed to address the aforementioned challenges and present satisfactory explanations on Natural Language Processing (…
As language technologies become more ubiquitous, there are increasing efforts towards expanding the language diversity and coverage of natural language processing (NLP) systems. Arguably, the most important factor influencing the quality of modern NLP systems is data availability. In this work, we study the geographical representativeness of NLP datasets, aiming to quantify if and by how much do NLP datasets match the expected needs of the language speakers. In doing so, we use entity recognition and linking systems, also making important observations about their cross-lingual consistency and …
Pretrained Transformer based models finetuned on domain specific corpora have changed the landscape of NLP. However, training or fine-tuning these models for individual tasks can be time consuming and resource intensive. Thus, a lot of current research is focused on using transformers for multi-task learning (Raffel et al.,2020) and how to group the tasks to help a multi-task model to learn effective representations that can be shared across tasks (Standley et al., 2020; Fifty et al., 2021). In this work, we show that a single multi-tasking model can match the performance of task specific mode…
Breakthroughs in transformer-based models have revolutionized not only the NLP field, but also vision and multimodal systems. However, although visualization and interpretability tools have become available for NLP models, internal mechanisms of vision and multimodal transformers remain largely opaque. With the success of these transformers, it is increasingly critical to understand their inner workings, as unraveling these black-boxes will lead to more capable and trustworthy models. To contribute to this quest, we propose VL-InterpreT, which provides novel interactive visualizations for inte…
Interpretability techniques in NLP have mainly focused on understanding individual predictions using attention visualization or gradient-based saliency maps over tokens. We propose using k nearest neighbor (kNN) representations to identify training examples responsible for a model's predictions and obtain a corpus-level understanding of the model's behavior. Apart from interpretability, we show that kNN representations are effective at uncovering learned spurious associations, identifying mislabeled examples, and improving the fine-tuned model's performance. We focus on Natural Language Infere…
Prompt4Vis: Prompting Large Language Models with Example Mining and Schema Filtering for Tabular Data Visualization
The Hong Kong Polytechnic University（香港理工大学）；University of Chinese Academy of Sciences（中国科学院大学）；The Hong Kong University of Science and Technology（香港科技大学）；WeBank Co., Ltd（微众银行）；University of Liverpool（利物浦大学）
针对自然语言转数据可视化查询性能不足的问题，提出基于大语言模型与上下文学习的 Prompt4Vis 框架，通过多目标示例挖掘和模式过滤模块显著提升了生成性能，在 NVBench 数据集上大幅超越现有 SOTA 方法。
University of Pittsburgh（匹兹堡大学）；University of Utah（犹他大学）
Natural Language Processing (NLP) systems often make use of machine learning techniques that are unfamiliar to end-users who are interested in analyzing clinical records. Although NLP has been widely used in extracting information from clinical text, current systems generally do not support model revision based on feedback from domain experts. We present a prototype tool that allows end users to visualize and review the outputs of an NLP system that extracts binary variables from clinical text. Our tool combines multiple visualizations to help the users understand these results and make any ne…
Challenges in Explaining Pretrained Clinical Text Classifiers
Faculty of Computer and Information Science, University of Ljubljana, Slovenia（卢布尔雅那大学计算机与信息科学学院）；ICAM - Advanced Environmental Research Institute, West University of Timisoara, Romania（蒂米什瓦德西大学先进环境研究所）
Topological Data Analysis (TDA) is a novel new and fast growing field of data science providing a set of new topological and geometric tools to derive relevant features out of complex high-dimensional data. In this paper we apply two of best methods in topological data analysis, "Persistent Homology" and "Mapper", in order to classify persian poems which has been composed by two of the best Iranian poets namely "Ferdowsi" and "Hafez". This article has two main parts, in the first part we explain the mathematics behind these two methods which is easy to understand for general audience and in th…
Previous works show that deep NLP models are not always conceptually sound: they do not always learn the correct linguistic concepts. Specifically, they can be insensitive to word order. In order to systematically evaluate models for their conceptual soundness with respect to word order, we introduce a new explanation method for sequential data: Order-sensitive Shapley Values (OSV). We conduct an extensive empirical evaluation to validate the method and surface how well various deep NLP models learn word order. Using synthetic data, we first show that OSV is more faithful in explaining model b…
DataNarrative: Automated Data-Driven Storytelling with Visualizations and Texts
York University（约克大学）；Qatar Computing Research Institute (QCRI)（卡塔尔计算研究所）；Nanyang Technological University（南洋理工大学）；Dialpad Inc.（Dialpad公司）；Salesforce AI（Salesforce人工智能部门）
Neural language models have achieved human level performance across several NLP datasets. However, recent studies have shown that these models are not truly learning the desired task; rather, their high performance is attributed to overfitting using spurious biases, which suggests that the capabilities of AI systems have been over-estimated. We introduce a generic formula for Data Quality Index (DQI) to help dataset creators create datasets free of such unwanted biases. We evaluate this formula using a recently proposed approach for adversarial filtering, AFLite. We propose a new data creation…
Extreme pricing anomalies may occur unexpectedly without a trivial cause, and equity traders typically experience a meticulous process to source disparate information and analyze its reliability before integrating it into the trusted knowledge base. We introduce DeepTrust, a reliable financial knowledge retrieval framework on Twitter to explain extreme price moves at speed, while ensuring data veracity using state-of-the-art NLP techniques. Our proposed framework consists of three modules, specialized for anomaly detection, information retrieval and reliability assessment. The workflow starts …
