Collaborating Authors


Best Public Datasets for Machine Learning and Data Science


This resource is continuously updated. If you know any other suitable and open datasets, please let us know by emailing us at or by dropping a comment below. Google Dataset Search: Similar to how Google Scholar works, Dataset Search lets you find datasets wherever they are hosted, whether it's a publisher's site, a digital library, or an author's web page. It's a phenomenal dataset finder, and it contains over 25 million datasets. Kaggle: Kaggle provides a vast container of datasets, sufficient for the enthusiast to the expert.

A High Schooler's Guide To Deep Learning And AI


The idea of creating a virtual human that can converse seamlessly with a user seems daunting to most people who are just getting into artificial intelligence and looking into how utterly complex existing commercial systems are. And their fears aren't misled - larger systems that contain a plethora of data samples and an intricate network architecture, and are responsible for providing the highest quality home assistant system are very difficult to replicate. But, creating virtual assistants at a smaller level has already been simplified to allow virtually anyone to make their own conversational persona. Over the past decade, the University of Southern California's Institute for Creative Technologies has developed countless virtual personalities for a variety of reasons: The institute has been able to create the amount of virtual humans as they have because of the technology they developed titled'NPCEditor'. As the name implies, the program allows the team to edit an NPC, or non-player-character. Developed by research scientist Anton Leuski and lead professor of NLP David Traum, the software has been simplified enough so that it is incredibly easy to create a virtual human.

Natural Language Processing


Chapter 5 of this free 15 chapter AI handbook provides an overview of natural language processing.

Mining Knowledge Graphs From Incident Reports Artificial Intelligence

Incident management is a critical part of the DevOps processes for developing and operating large-scale services in the cloud. Incident reports filed by customers are largely unstructured making any automated diagnosis or mitigation non-trivial. It requires on-call engineers to parse verbose reports to understand the issue and locate key information. Prior work has looked into extraction of key attributes or entities like error codes, tenant Ids, stack traces, etc. from incident and bug reports. Although a flat list of entities is informative, to unlock the full potential of knowledge extraction, it is necessary to provide context to these entities. For instance, the relations between the real-world concepts or objects that these entities represent in otherwise unstructured data is useful for downstream tasks like incident linking, triaging and mitigation. With this additional context, entities are transformed from "Strings" to "Things". In this work, we present an approach to mine and score binary entity relations from co-occurring entity pairs. We evaluate binary relations extracted and show that our approach has a high precision of 0.9. Further, we construct knowledge graphs automatically and show that the implicit knowledge in the graph can be used to mine and rank relevant entities for distinct incidents, by mapping entities to clusters of incident titles.

Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making Artificial Intelligence

Although AI holds promise for improving human decision making in societally critical domains, it remains an open question how human-AI teams can reliably outperform AI alone and human alone in challenging prediction tasks (also known as complementary performance). We explore two directions to understand the gaps in achieving complementary performance. First, we argue that the typical experimental setup limits the potential of human-AI teams. To account for lower AI performance out-of-distribution than in-distribution because of distribution shift, we design experiments with different distribution types and investigate human performance for both in-distribution and out-of-distribution examples. Second, we develop novel interfaces to support interactive explanations so that humans can actively engage with AI assistance. Using in-person user study and large-scale randomized experiments across three tasks, we demonstrate a clear difference between in-distribution and out-of-distribution, and observe mixed results for interactive explanations: while interactive explanations improve human perception of AI assistance's usefulness, they may magnify human biases and lead to limited performance improvement. Overall, our work points out critical challenges and future directions towards complementary performance.

EventPlus: A Temporal Event Understanding Pipeline Artificial Intelligence

We present EventPlus, a temporal event understanding pipeline that integrates various state-of-the-art event understanding components including event trigger and type detection, event argument detection, event duration and temporal relation extraction. Event information, especially event temporal knowledge, is a type of common sense knowledge that helps people understand how stories evolve and provides predictive hints for future events. EventPlus as the first comprehensive temporal event understanding pipeline provides a convenient tool for users to quickly obtain annotations about events and their temporal information for any user-provided document. Furthermore, we show EventPlus can be easily adapted to other domains (e.g., biomedical domain). We make EventPlus publicly available to facilitate event-related information extraction and downstream applications.

Socially Responsible AI Algorithms: Issues, Purposes, and Challenges Artificial Intelligence

In the current era, people and society have grown increasingly reliant on Artificial Intelligence (AI) technologies. AI has the potential to drive us towards a future in which all of humanity flourishes. It also comes with substantial risks for oppression and calamity. Discussions about whether we should (re)trust AI have repeatedly emerged in recent years and in many quarters, including industry, academia, health care, services, and so on. Technologists and AI researchers have a responsibility to develop trustworthy AI systems. They have responded with great efforts of designing more responsible AI algorithms. However, existing technical solutions are narrow in scope and have been primarily directed towards algorithms for scoring or classification tasks, with an emphasis on fairness and unwanted bias. To build long-lasting trust between AI and human beings, we argue that the key is to think beyond algorithmic fairness and connect major aspects of AI that potentially cause AI's indifferent behavior. In this survey, we provide a systematic framework of Socially Responsible AI Algorithms that aims to examine the subjects of AI indifference and the need for socially responsible AI algorithms, define the objectives, and introduce the means by which we may achieve these objectives. We further discuss how to leverage this framework to improve societal well-being through protection, information, and prevention/mitigation.

Robustness Gym: Unifying the NLP Evaluation Landscape Artificial Intelligence

Despite impressive performance on standard benchmarks, deep neural networks are often brittle when deployed in real-world systems. Consequently, recent research has focused on testing the robustness of such models, resulting in a diverse set of evaluation methodologies ranging from adversarial attacks to rule-based data transformations. In this work, we identify challenges with evaluating NLP systems and propose a solution in the form of Robustness Gym (RG), a simple and extensible evaluation toolkit that unifies 4 standard evaluation paradigms: subpopulations, transformations, evaluation sets, and adversarial attacks. By providing a common platform for evaluation, Robustness Gym enables practitioners to compare results from all 4 evaluation paradigms with just a few clicks, and to easily develop and share novel evaluation methods using a built-in set of abstractions. To validate Robustness Gym's utility to practitioners, we conducted a real-world case study with a sentiment-modeling team, revealing performance degradations of 18%+. To verify that Robustness Gym can aid novel research analyses, we perform the first study of state-of-the-art commercial and academic named entity linking (NEL) systems, as well as a fine-grained analysis of state-of-the-art summarization models. For NEL, commercial systems struggle to link rare entities and lag their academic counterparts by 10%+, while state-of-the-art summarization models struggle on examples that require abstraction and distillation, degrading by 9%+. Robustness Gym can be found at

"Brilliant AI Doctor" in Rural China: Tensions and Challenges in AI-Powered CDSS Deployment Artificial Intelligence

Artificial intelligence (AI) technology has been increasingly used in the implementation of advanced Clinical Decision Support Systems (CDSS). Research demonstrated the potential usefulness of AI-powered CDSS (AI-CDSS) in clinical decision making scenarios. However, post-adoption user perception and experience remain understudied, especially in developing countries. Through observations and interviews with 22 clinicians from 6 rural clinics in China, this paper reports the various tensions between the design of an AI-CDSS system ("Brilliant Doctor") and the rural clinical context, such as the misalignment with local context and workflow, the technical limitations and usability barriers, as well as issues related to transparency and trustworthiness of AI-CDSS. Despite these tensions, all participants expressed positive attitudes toward the future of AI-CDSS, especially acting as "a doctor's AI assistant" to realize a Human-AI Collaboration future in clinical settings. Finally we draw on our findings to discuss implications for designing AI-CDSS interventions for rural clinical contexts in developing countries.

Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals Artificial Intelligence

Multi-hop Knowledge Base Question Answering (KBQA) aims to find the answer entities that are multiple hops away in the Knowledge Base (KB) from the entities in the question. A major challenge is the lack of supervision signals at intermediate steps. Therefore, multi-hop KBQA algorithms can only receive the feedback from the final answer, which makes the learning unstable or ineffective. To address this challenge, we propose a novel teacher-student approach for the multi-hop KBQA task. In our approach, the student network aims to find the correct answer to the query, while the teacher network tries to learn intermediate supervision signals for improving the reasoning capacity of the student network. The major novelty lies in the design of the teacher network, where we utilize both forward and backward reasoning to enhance the learning of intermediate entity distributions. By considering bidirectional reasoning, the teacher network can produce more reliable intermediate supervision signals, which can alleviate the issue of spurious reasoning. Extensive experiments on three benchmark datasets have demonstrated the effectiveness of our approach on the KBQA task.