As artificial intelligence (AI) systems become increasingly deployed across the world, they are also increasingly implicated in AI incidents – harm events to individuals and society. As a result, industry, civil society, and governments worldwide are developing best practices and regulations for monitoring and analyzing AI incidents. The AI Incident Database (AIID) is a project that catalogs AI incidents and supports further research by providing a platform to classify incidents for different operational and research-oriented goals. This study reviews the AIID’s dataset of 750+ AI incidents and two independent taxonomies applied to these incidents to identify common challenges to indexing and analyzing AI incidents. We find that certain patterns of AI incidents present structural ambiguities that challenge incident databasing and explore how epistemic uncertainty in AI incident reporting is unavoidable. We therefore report mitigations to make incident processes more robust to uncertainty related to cause, extent of harm, severity, or technical details of implicated systems. With these findings, we discuss how to develop future AI incident reporting practices.

Abstract The recent breakthroughs in deep neural architectures across multiple machine learning fields have led to the widespread use of deep neural models. These learners are often applied as black-box models that ignore or insufficiently utilize a wealth of preexisting semantic information. In this study, we focus on the text classification task, investigating methods for augmenting the input to deep neural networks (DNNs) with semantic information. We extract semantics for the words in the preprocessed text from the WordNet semantic graph, in the form of weighted concept terms that form a semantic frequency vector. Concepts are selected via a variety of semantic disambiguation techniques, including a basic, a part-of-speech-based, and a semantic embedding projection method. Additionally, we consider a weight propagation mechanism that exploits semantic relationships in the concept graph and conveys a spreading activation component. We enrich word2vec embeddings with the resulting semantic vector through concatenation or replacement and apply the semantically augmented word embeddings on the classification task via a DNN. Experimental results over established datasets demonstrate that our approach of semantic augmentation in the input space boosts classification performance significantly, with concatenation offering the best performance. We also note additional interesting findings produced by our approach regarding the behavior of term frequency - inverse document frequency normalization on semantic vectors, along with the radical dimensionality reduction potential with negligible performance loss.

JedAI is an open-source toolkit that allows for building and benchmarking thousands of schema-agnostic Entity Resolution (ER) pipelines through a non-learning, blocking-based end-to-end workflow. In this paper, we present its latest release, JedAI3 , which conveys two new end-to-end workflows: one for budgetagnostic ER that is based on similarity joins, and one for budgetaware (i.e., progressive) ER. This version also adds support for pre-trained word or character embeddings and connects JedAI to the Python data analysis ecosystem. Overall, these enhancements provide JedAI with features offered by no other ER tool, especially in the schema- and domain-agnostic context.

This work examines document clustering as a record linkage problem, focusing on named-entities and frequent terms, using several vector and graph-based document representation methods and k-means clustering with different similarity measures. The JedAI Record Linkage toolkit is employed for most of the record linkage pipeline tasks (i.e. preprocessing, scalable feature representation, blocking and clustering) and the OpenCalais platform for entity extraction. The resulting clusters are evaluated with multiple clustering quality metrics. The experiments show very good clustering results and significant speedups in the clustering process, which indicates the suitability of both the record linkage formulation and the JedAI toolkit for improving the scalability for large-scale document clustering tasks.

This work investigates the effectiveness of a state-of-the-art concept detection framework for the automatic classification of multimedia content, namely images and videos, embedded in publicly available Web resources containing recipes for the synthesis of Home Made Explosives (HMEs), to a set of predefined semantic concepts relevant to the HME domain. The concept detection framework employs advanced methods for video (shot) segmentation, visual feature extraction (using SIFT, SURF, and their variations), and classification based on machine learning techniques (logistic regression). The evaluation experiments are performed using an annotated collection of multimedia HME content discovered on the Web, and a set of concepts, which emerged both from an empirical study, and were also provided by domain experts and interested stakeholders, including Law Enforcement Agencies personnel. The experiments demonstrate the satisfactory performance of our framework, which in turn indicates the significant potential of the adopted approaches on the HME domain.