Timnit Gebru is one of the leading voices working on ethics in artificial intelligence. Her research has explored ways to combat biases, such as racism and sexism, that creep into AI through flawed data and creators. At Google, she and colleague Margaret Mitchell ran a team focused on the subject--until they tried to publish a paper critical of Google products and were dismissed. Now Gebru, a founder of the affinity group Black in AI, is lining up backers for an independent AI research group. Calls to hold Big Tech accountable for its products and practices, she says, can't all be made from inside the house.

Pre-trained language models have been found to capture a surprisingly rich amount of lexical knowledge, ranging from commonsense properties of everyday concepts to detailed factual knowledge about named entities. Among others, this makes it possible to distill high-quality word vectors from pre-trained language models. However, it is currently unclear to what extent it is possible to distill relation embeddings, i.e. vectors that characterize the relationship between two words. Such relation embeddings are appealing because they can, in principle, encode relational knowledge in a more fine-grained way than is possible with knowledge graphs. To obtain relation embeddings from a pre-trained language model, we encode word pairs using a (manually or automatically generated) prompt, and we fine-tune the language model such that relationally similar word pairs yield similar output vectors. We find that the resulting relation embeddings are highly competitive on analogy (unsupervised) and relation classification (supervised) benchmarks, even without any task-specific fine-tuning. Source code to reproduce our experimental results and the model checkpoints are available in the following repository: https://github.com/asahi417/relbert

AI, machine learning, and data science methods are already pervasive in our society and technology, affecting all of our lives in many subtle ways. Trustworthy AI has become an important topic because trust in AI systems and their creators has been lost, or was never present in the first place. Researchers, corporations, and governments have long and painful histories of excluding marginalized groups from technology development, deployment, and oversight. As a direct result of this exclusion, these technologies have long histories of being less useful or even harmful to minoritized groups. This infuriating history illustrates that industry cannot be trusted to self-regulate and why trust in commercial AI systems and development has been lost. We argue that any AI development, deployment, and monitoring framework that aspires to trust must incorporate both feminist, non-exploitative participatory design principles and strong, outside, and continual monitoring and testing. We additionally explain the importance of considering aspects of trustworthiness beyond just transparency, fairness, and accountability, specifically, to consider justice and shifting power to the people and disempowered as core values to any trustworthy AI system. Creating trustworthy AI starts by funding, supporting, and empowering groups like Queer in AI so the field of AI has the diversity and inclusion to credibly and effectively develop trustworthy AI. Through our years of work and advocacy, we have developed expert knowledge around questions of if and how gender, sexuality, and other aspects of identity should be used in AI systems and how harms along these lines should be mitigated. Based on this, we discuss a gendered approach to AI, and further propose a queer epistemology and analyze the benefits it can bring to AI.

Algorithmic recommendations and decisions have become ubiquitous in today's society. Many of these and other data-driven policies are based on known, deterministic rules to ensure their transparency and interpretability. This is especially true when such policies are used for public policy decision-making. For example, algorithmic pre-trial risk assessments, which serve as our motivating application, provide relatively simple, deterministic classification scores and recommendations to help judges make release decisions. Unfortunately, existing methods for policy learning are not applicable because they require existing policies to be stochastic rather than deterministic. We develop a robust optimization approach that partially identifies the expected utility of a policy, and then finds an optimal policy by minimizing the worst-case regret. The resulting policy is conservative but has a statistical safety guarantee, allowing the policy-maker to limit the probability of producing a worse outcome than the existing policy. We extend this approach to common and important settings where humans make decisions with the aid of algorithmic recommendations. Lastly, we apply the proposed methodology to a unique field experiment on pre-trial risk assessments. We derive new classification and recommendation rules that retain the transparency and interpretability of the existing risk assessment instrument while potentially leading to better overall outcomes at a lower cost.

As artificial intelligence enters the legal space, it is essential to recognize biases in legal data and ensure that they are not replicated and reinforced with legal technology [7, 13, 18]. Furthermore, understanding biases in legal data and developing discrimination-free technology could help the legal space to become fairer and more widely accessible. We typically find two types of biases in legal data: First, representation biases, i.e., certain social groups are over-or underrepresented in a data set. Second, sentencing disparities, i.e., the outcome of legal proceedings for similar cases varies across social groups. Representation biases may reflect disparities in policing (arrest rates) or in offense rates.

Last week, Activision Blizzard employees and the Communications Workers of America (CWA), a major media labor union, filed an unfair labor practice lawsuit against Activision Blizzard accusing the video game company of worker intimidation and union busting. The union claims Activision Blizzard is using coercive tactics to stop employees from unionizing. On the same day, while not commenting on the unfair labor suit, the company announced the hiring of two new senior executives: Julie Hodges, a human resources executive from Disney, as chief people officer and Sandeep Dube, former revenue management executive at Delta Air Lines, as chief commercial officer.

This is the web version of Eye on A.I., Fortune's weekly newsletter covering artificial intelligence and business. To get it delivered weekly to your in-box, sign up here. In January 2020, in a Fortune magazine cover story, I chronicled the corporate race for artificial general intelligence, a kind of human-like or even superhuman A.I. that is the staple of science fiction. The pursuit of AGI, as it's more commonly called, has led to many of the machine learning innovations that underpin the current A.I. boom. But that boom is centered around narrow A.I--software that can perform one, specific task well.

Oasis, IaaS and eDiscovery solutions provider, is proud to announce a new, long-term licensing agreement with global legal and compliance technology company Relativity, adding Analytics to its Relativity 11 offering within their robust suite of text analytics solutions. With Analytics already fully integrated into RelativityOne, this addition now provides clients the option of selecting Relativity 11 or RelativityOne without limitation on the use of analytics functionality. Relativity leads the way for AI-assisted document review and text analytics technology in eDiscovery. It is well known for its workflow efficiency, project management capabilities, and defensible results. "Relativity has been a great software partner over the years and this move further solidifies our relationship," said Brandon Law, Oasis Founder and CEO.

Ethical principles aren't enough to defend against the worst potential impacts of artificial intelligence systems and the time has come for the U.S. to establish official legal policies for this emerging technology, said policy and technology experts during a recent report launch event from New America's Open Technology Institute. That work requires clearly defining terms and enforcement measures, and speakers sought to propose mechanisms that can help government promote fairness, accountability and transparency (FAT) in algorithmic systems, as well as outline the challenges that lie ahead. They called for the federal government to regulate how private firms like online content platforms develop and leverage AI as well as establish formal policies for overseeing and vetting the algorithmic systems public agencies adopt and purchase. Such AI audits are currently voluntary, said Spandana Singh, policy analyst at the Open Technology Institute and co-author of the report. AI can deliver newfound efficiencies, extract meaning from troves of data and deliver a variety of other benefits, but the complexity, opacity and lack of foresight in some of these systems means they can be designed, implemented or evolve in ways that produce biased and discriminatory effects.

AI is becoming more and more prevalent in society, with many people wondering how it will affect the law. How artificial intelligence is impacting our laws and what we can expect for future technology/legal interactions. The conversation surrounding the relationship between AI and law also touches quite clearly on the ability to rely on Artificial Intelligence to deliver fair decisions and to enhance the legal system's delivery of equity and justice. In this article, I share insights from my conversations on this topic with Joilson Melo, a Brazilian law expert, and programmer whose devotion to equity and fairness led to a historic change in the Brazilian legal system in 2019, this change mainly affected the system that controls all processes processed digitally in Brazil, the PJe (Electronic Judicial Process). As a law student, Melo filed a request for action in the National Council of Justice (CNJ) against the Court of Justice of Mato Grosso, resulting in a decision allowing citizens to file applications in court electronically without a lawyer and within the Special Court, observing the value of the case, so that it does not exceed 20 minimum wages.