In this paper, we investigate the computational intelligibility of Boolean classifiers, characterized by their ability to answer XAI queries in polynomial time. The classifiers under consideration are decision trees, DNF formulae, decision lists, decision rules, tree ensembles, and Boolean neural nets. Using 9 XAI queries, including both explanation queries and verification queries, we show the existence of large intelligibility gap between the families of classifiers. On the one hand, all the 9 XAI queries are tractable for decision trees. On the other hand, none of them is tractable for DNF formulae, decision lists, random forests, boosted decision trees, Boolean multilayer perceptrons, and binarized neural networks.

In critical situations involving discrimination, gender inequality, economic damage, and even the possibility of casualties, machine learning models must be able to provide clear interpretations for their decisions. Otherwise, their obscure decision-making processes can lead to socioethical issues as they interfere with people's lives. In the aforementioned sectors, random forest algorithms strive, thus their ability to explain themselves is an obvious requirement. In this paper, we present LionForests, which relies on a preliminary work of ours. LionForests is a random forest-specific interpretation technique, which provides rules as explanations. It is applicable from binary classification tasks to multi-class classification and regression tasks, and it is supported by a stable theoretical background. Experimentation, including sensitivity analysis and comparison with state-of-the-art techniques, is also performed to demonstrate the efficacy of our contribution. Finally, we highlight a unique property of LionForests, called conclusiveness, that provides interpretation validity and distinguishes it from previous techniques.

We consider the problem of sequentially allocating resources in a censored semi-bandits setup, where the learner allocates resources at each step to the arms and observes loss. The loss depends on two hidden parameters, one specific to the arm but independent of the resource allocation, and the other depends on the allocated resource. More specifically, the loss equals zero for an arm if the resource allocated to it exceeds a constant (but unknown) arm dependent threshold. The goal is to learn a resource allocation that minimizes the expected loss. The problem is challenging because the loss distribution and threshold value of each arm are unknown. We study this setting by establishing its `equivalence' to Multiple-Play Multi-Armed Bandits (MP-MAB) and Combinatorial Semi-Bandits. Exploiting these equivalences, we derive optimal algorithms for our problem setting using known algorithms for MP-MAB and Combinatorial Semi-Bandits. The experiments on synthetically generated data validate the performance guarantees of the proposed algorithms.

Major advancement in the performance of machine translation models has been made possible in part thanks to the availability of large-scale parallel corpora. But for most languages in the world, the existence of such corpora is rare. Emakhuwa, a language spoken in Mozambique, is like most African languages low-resource in NLP terms. It lacks both computational and linguistic resources and, to the best of our knowledge, few parallel corpora including Emakhuwa already exist. In this paper we describe the creation of the Emakhuwa-Portuguese parallel corpus, which is a collection of texts from the Jehovah's Witness website and a variety of other sources including the African Story Book website, the Universal Declaration of Human Rights and Mozambican legal documents. The dataset contains 47,415 sentence pairs, amounting to 699,976 word tokens of Emakhuwa and 877,595 word tokens in Portuguese. After normalization processes which remain to be completed, the corpus will be made freely available for research use.

In this paper, We present our approach for IEEEBigMM 2020, Grand Challenge (BMGC), Identifying senti-ments from tweets related to the MeToo movement. The modelis based on an ensemble of Convolutional Neural Network,Bidirectional LSTM and a DNN for final classification. Thispaper is aimed at providing a detailed analysis of the modeland the results obtained. We have ranked 5th out of 10 teamswith a score of 0.51491

A. Relevance of Model Explanations in Real-World Contexts Complex estimation and decision-making tasks have traditionally been analyzed and judged by human experts. Hence, decisions have typically been able to be complemented with human-interpretable justifications, when needed, as experts can normally explain the line-of-thought that led to their own decision-making. However, in the past two decades, algorithmic decision-making has spread increasingly to many relevant societal contexts. Despite the notable enthusiasm for the potential benefit that this type of technology can bring, the underlying methods used are typically not inherently transparent, in the sense that they do not readily provide human-interpretable justifications for their decisions [1]. Moreover, in recent years there is a trend where the most successful algorithms, particularly in complex tasks like machine vision and natural language processing, tend to rely on highly complex models, which has led to a further increase in tension between accuracy and interpretability [2]. Relevant societal contexts where algorithmic decision systems have gained substantial traction include medical diagnosis and treatment [3], counter-terrorism [4], criminal justice [5], and risk assessments for credits and insurance [6]. In such impactful contexts, there is a legitimate need for providing human-interpretable explanations along with the estimations and decisions made. Indeed, lack of interpretability has become a barrier to the adoption of machine learning-based systems in many institutions and companies. Hence the value of complementing ML models with human-interpretable accounts of the statistical rationals behind their estimations, in a way that human decision-makers can more easily understand machine estimations, and even integrate their statistical rationals with qualitative information and human expert judgements.

Technologies like AI, blockchain, cognitive computing, and advanced data analytics will be a boon for the judicial system in many ways. Countries are even thinking about robot judges.

Artificial intelligence (AI) is set to transform many aspects of our lives, including our home and health. AI is already widely used in internet searches, and home devices with speech recognition, but in the near future we will see AI become even more widespread. This will have significant repercussions as AI performs many tasks that until now could only be undertaken by humans. AI will remove human intervention from much of the picture. This will particularly affect intellectual property law.

We have since a long time ago advanced beyond a period when propels in AI research were bound to the lab. Artificial intelligence has now become a real-world application technology and part of current life. If harnessed properly, we trust AI can convey extraordinary advantages for economies and society, and support decision-making, which is more attractive, secure and more comprehensive and educated. Yet, such promise won't be acknowledged without extraordinary consideration and effort, which incorporates regulations in AI and governance of AI. It should also focus on how its development and utilization ought to be governed, and what level of legal and moral management-- by whom, and when, is required.

This paper aims to provide an overview of the ethical concerns in artificial intelligence (AI) and the framework that is needed to mitigate those risks, and to suggest a practical path to ensure the development and use of AI at the United Nations (UN) aligns with our ethical values. The overview discusses how AI is an increasingly powerful tool with potential for good, albeit one with a high risk of negative side-effects that go against fundamental human rights and UN values. It explains the need for ethical principles for AI aligned with principles for data governance, as data and AI are tightly interwoven. It explores different ethical frameworks that exist and tools such as assessment lists. It recommends that the UN develop a framework consisting of ethical principles, architectural standards, assessment methods, tools and methodologies, and a policy to govern the implementation and adherence to this framework, accompanied by an education program for staff.