Lattices and their order diagrams are an essential tool for communicating knowledge and insights about data. This is in particular true when applying Formal Concept Analysis. Such representations, however, are difficult to comprehend by untrained users and in general in cases where lattices are large. We tackle this problem by automatically generating textual explanations for lattices using standard scales. Our method is based on the general notion of ordinal motifs in lattices for the special case of standard scales. We show the computational complexity of identifying a small number of standard scales that cover most of the lattice structure. For these, we provide textual explanation templates, which can be applied to any occurrence of a scale in any data domain. These templates are derived using principles from human-computer interaction and allow for a comprehensive textual explanation of lattices. We demonstrate our approach on the spices planner data set, which is a medium sized formal context comprised of fifty-six meals (objects) and thirty-seven spices (attributes). The resulting 531 formal concepts can be covered by means of about 100 standard scales.
Contrastive explanation methods go beyond transparency and address the contrastive aspect of explanations. Such explanations are emerging as an attractive option to provide actionable change to scenarios adversely impacted by classifiers' decisions. However, their extension to textual data is under-explored and there is little investigation on their vulnerabilities and limitations. This work motivates textual counterfactuals by laying the ground for a novel evaluation scheme inspired by the faithfulness of explanations. Accordingly, we extend the computation of three metrics, proximity,connect…
Textual Explanations and Their Evaluations for Reinforcement Learning Policy
Ericsson Research（爱立信研究）；Ericsson AB（爱立信公司）；KTH Royal Institute of Technology（皇家理工学院）；Uppsala University（乌普萨拉大学）；Global AI Accelerator（全球人工智能加速器）；Ericsson Inc.（爱立信公司）
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）
Explainable deep learning models are advantageous in many situations. Prior work mostly provide unimodal explanations through post-hoc approaches not part of the original system design. Explanation mechanisms also ignore useful textual information present in images. In this paper, we propose MTXNet, an end-to-end trainable multimodal architecture to generate multimodal explanations, which focuses on the text in the image. We curate a novel dataset TextVQA-X, containing ground truth visual and multi-reference textual explanations that can be leveraged during both training and evaluation. We the…
LangXAI: Integrating Large Vision Models for Generating Textual Explanations to Enhance Explainability in Visual Perception Tasks
University of New Brunswick（新不伦瑞克大学）；Quy Nhon AI, FPT Software（FPT软件公司归仁人工智能部门）；Friedrich-Alexander-University Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；Software AG（软件AG公司）
LangXAI 框架将 XAI 与先进视觉模型结合，为分类、检测和分割任务生成文本解释，以高 BERTScore 验证其合理性，从而提升终端用户对视觉 AI 的理解与信任。
UC Berkeley（加州大学伯克利分校）；University of Amsterdam（阿姆斯特丹大学）；MPI for Informatics（马克斯·普朗克信息学研究所）；Facebook AI Research（脸书人工智能研究院）
Deep models that are both effective and explainable are desirable in many settings; prior explainable models have been unimodal, offering either image-based visualization of attention weights or text-based generation of post-hoc justifications. We propose a multimodal approach to explanation, and argue that the two modalities provide complementary explanatory strengths. We collect two new datasets to define and evaluate this task, and propose a novel model which can provide joint textual rationale generation and attention visualization. Our datasets define visual and textual justifications of …
University of Oxford（牛津大学）；Alan Turing Institute（艾伦·图灵研究所）；University of Tuebingen（图宾根大学）
The recently proposed SNLI-VE corpus for recognising visual-textual entailment is a large, real-world dataset for fine-grained multimodal reasoning. However, the automatic way in which SNLI-VE has been assembled (via combining parts of two related datasets) gives rise to a large number of errors in the labels of this corpus. In this paper, we first present a data collection effort to correct the class with the highest error rate in SNLI-VE. Secondly, we re-evaluate an existing model on the corrected corpus, which we call SNLI-VE-2.0, and provide a quantitative comparison with its performance o…
End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations
School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院）；State Key Laboratory of General Artificial Intelligence, BIGAI（北京智源人工智能研究院通用人工智能国家重点实验室）
In this paper, we propose a method to obtain robust explanations for visual question answering(VQA) that correlate well with the answers. Our model explains the answers obtained through a VQA model by providing visual and textual explanations. The main challenges that we address are i) Answers and textual explanations obtained by current methods are not well correlated and ii) Current methods for visual explanation do not focus on the right location for explaining the answer. We address both these challenges by using a collaborative correlated module which ensures that even if we do not train …
University of Antwerp（安特卫普大学）；Stern School of Business (NYU)（纽约大学斯特恩商学院）；INSEAD Paris（欧洲工商管理学院巴黎校区）
We study the interpretability of predictive systems that use high-dimensonal behavioral and textual data. Examples include predicting product interest based on online browsing data and detecting spam emails or objectionable web content. Recently, counterfactual explanations have been proposed for generating insight into model predictions, which focus on what is relevant to a particular instance. Conducting a complete search to compute counterfactuals is very time-consuming because of the huge dimensionality. To our knowledge, for behavioral and text data, only one model-agnostic heuristic algo…
New Jersey Institute of Technology（新泽西理工学院）；Wells Fargo Bank（富国银行）；University of Oregon（俄勒冈大学）
In this paper, we introduce a novel interpreting framework that learns an interpretable model based on an ontology-based sampling technique to explain agnostic prediction models. Different from existing approaches, our algorithm considers contextual correlation among words, described in domain knowledge ontologies, to generate semantic explanations. To narrow down the search space for explanations, which is a major problem of long and complicated text data, we design a learnable anchor algorithm, to better extract explanations locally. A set of regulations is further introduced, regarding comb…
In this extended abstract we discuss the opportunities and challenges of studying intrinsically-motivated agents for exploration in textual environments. We argue that there is important synergy between text environments and autonomous agents. We identify key properties of text worlds that make them suitable for exploration by autonmous agents, namely, depth, breadth, progress niches and the ease of use of language goals; we identify drivers of exploration for such agents that are implementable in text worlds. We discuss the opportunities of using autonomous agents to make progress on text env…
Machine learning models on behavioral and textual data can result in highly accurate prediction models, but are often very difficult to interpret. Rule-extraction techniques have been proposed to combine the desired predictive accuracy of complex "black-box" models with global explainability. However, rule-extraction in the context of high-dimensional, sparse data, where many features are relevant to the predictions, can be challenging, as replacing the black-box model by many rules leaves the user again with an incomprehensible explanation. To address this problem, we develop and test a rule-…
Depression is a global mental health problem, the worst case of which can lead to suicide. An automatic depression detection system provides great help in facilitating depression self-assessment and improving diagnostic accuracy. In this work, we propose a novel depression detection approach utilizing speech characteristics and linguistic contents from participants' interviews. In addition, we establish an Emotional Audio-Textual Depression Corpus (EATD-Corpus) which contains audios and extracted transcripts of responses from depressed and non-depressed volunteers. To the best of our knowledge…
Edinburgh Centre for Robotics（爱丁堡机器人中心）；Heriot-Watt University（赫瑞-瓦特大学）；University of Edinburgh（爱丁堡大学）
As transparency becomes key for robotics and AI, it will be necessary to evaluate the methods through which transparency is provided, including automatically generated natural language (NL) explanations. Here, we explore parallels between the generation of such explanations and the much-studied field of evaluation of Natural Language Generation (NLG). Specifically, we investigate which of the NLG evaluation measures map well to explanations. We present the ExBAN corpus: a crowd-sourced corpus of NL explanations for Bayesian Networks. We run correlations comparing human subjective ratings with …
Open AI's language model, GPT-3, has shown great potential for many NLP tasks, with applications in many different domains. In this work we carry out a first study on GPT-3's capability to communicate musical decisions through textual explanations when prompted with a textual representation of a piece of music. Enabling a dialogue in human-AI music partnerships is an important step towards more engaging and creative human-AI interactions. Our results show that GPT-3 lacks the necessary intelligence to really understand musical decisions. A major barrier to reach a better performance is the lac…
Indian Statistical Institute（印度统计研究所）；Calcutta University（加尔各答大学）
There is enormous growth in various fields of research. This development is accompanied by new problems. To solve these problems efficiently and in an optimized manner, algorithms are created and described by researchers in the scientific literature. Scientific algorithms are vital for understanding and reusing existing work in numerous domains. However, algorithms are generally challenging to find. Also, the comparison among similar algorithms is difficult because of the disconnected documentation. Information about algorithms is mostly present in websites, code comments, and so on. There is …
Georgia Institute of Technology（佐治亚理工学院）；Allen Institute for AI（艾伦人工智能研究所）；University of Washington（华盛顿大学）
Explainable NLP (ExNLP) has increasingly focused on collecting human-annotated textual explanations. These explanations are used downstream in three ways: as data augmentation to improve performance on a predictive task, as supervision to train models to produce explanations for their predictions, and as a ground-truth to evaluate model-generated explanations. In this review, we identify 65 datasets with three predominant classes of textual explanations (highlights, free-text, and structured), organize the literature on annotating each type, identify strengths and shortcomings of existing coll…
Waseda University（早稻田大学）；National Institute of Advanced Industrial Science and Technology (AIST)（产业技术综合研究所）；Waseda Research Institute for Science and Engineering（早稻田大学科学与工程研究院）
Due to the recent boom in artificial intelligence (AI) research, including computer vision (CV), it has become impossible for researchers in these fields to keep up with the exponentially increasing number of manuscripts. In response to this situation, this paper proposes the paper summary generation (PSG) task using a simple but effective method to automatically generate an academic paper summary from raw PDF data. We realized PSG by combination of vision-based supervised components detector and language-based unsupervised important sentence extractor, which is applicable for a trained format…
Investigating Acoustic-Textual Emotional Inconsistency Information for Automatic Depression Detection
Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院粤港澳人机协同智能系统联合实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Good Mood Health Industry Group Co., Ltd（好心情健康产业集团有限公司）；Shanghai Jiao Tong University（上海交通大学）
In this paper we present a process for automatically generating manuals for board games within the Ludii general game system. This process requires many different sub-tasks to be addressed, such as English translation of Ludii game descriptions, move visualisation, highlighting winning moves, strategy explanation, among others. These aspects are then combined to create a full manual for any given game. This manual is intended to provide a more intuitive explanation of a game's rules and mechanics, particularly for players who are less familiar with the Ludii game description language and gramm…
Automatic reasoning about textual information is a challenging task in modern Natural Language Processing (NLP) systems. In this work we describe our proposal for representing and reasoning about Portuguese documents by means of Linked Data like ontologies and thesauri. Our approach resorts to a specialized pipeline of natural language processing (part-of-speech tagger, named entity recognition, semantic role labeling) to populate an ontology for the domain of criminal investigations. The provided architecture and ontology are language independent. Although some of the NLP modules are language…
Aalto University（阿尔托大学）；The University of Auckland（奥克兰大学）
This article explores the natural language generation capabilities of large language models with application to the production of two types of learning resources common in programming courses. Using OpenAI Codex as the large language model, we create programming exercises (including sample solutions and test cases) and code explanations, assessing these qualitatively and quantitatively. Our results suggest that the majority of the automatically generated content is both novel and sensible, and in some cases ready to use as is. When creating exercises we find that it is remarkably easy to influ…
German Research Center for Artificial Intelligence (DFKI) GmbH（德国人工智能研究中心）；Technical University Kaiserslautern（凯泽斯劳滕工业大学）；University Hospital Münster（明斯特大学医院）；University Hospital of Düsseldorf（杜塞尔多夫大学医院）；School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST)（国立科技大学电气工程与计算机科学学院）；Deep Learning Laboratory, National Center of Artificial Intelligence（国家人工智能中心深度学习实验室）
One principal impediment in the successful deployment of AI-based Computer-Aided Diagnosis (CAD) systems in clinical workflows is their lack of transparent decision making. Although commonly used eXplainable AI methods provide some insight into opaque algorithms, such explanations are usually convoluted and not readily comprehensible except by highly trained experts. The explanation of decisions regarding the malignancy of skin lesions from dermoscopic images demands particular clarity, as the underlying medical problem definition is itself ambiguous. This work presents ExAID (Explainable AI f…
Faculty of Engineering of University of Porto (FEUP)（波尔图大学工程学院）；INESC TEC（波尔图工程学院科技与高等研究中心）；Faculty of Science of University of Porto (FCUP)（波尔图大学理学院）；UCP-ESB（葡萄牙天主教大学商业经济学院）
This paper addresses the problem of automatic emotion recognition in the scope of the One-Minute Gradual-Emotional Behavior challenge (OMG-Emotion challenge). The underlying objective of the challenge is the automatic estimation of emotion expressions in the two-dimensional emotion representation space (i.e., arousal and valence). The adopted methodology is a weighted ensemble of several models from both video and text modalities. For video-based recognition, two different types of visual cues (i.e., face and facial landmarks) were considered to feed a multi-input deep neural network. Regardin…
Interpretability of machine learning (ML) models becomes more relevant with their increasing adoption. In this work, we address the interpretability of ML based question answering (QA) models on a combination of knowledge bases (KB) and text documents. We adapt post hoc explanation methods such as LIME and input perturbation (IP) and compare them with the self-explanatory attention mechanism of the model. For this purpose, we propose an automatic evaluation paradigm for explanation methods in the context of QA. We also conduct a study with human annotators to evaluate whether explanations help…
