Extracting informative arguments of events from news articles is a challenging problem in information extraction, which requires a global contextual understanding of each document. While recent work on document-level extraction has gone beyond single-sentence and increased the cross-sentence inference capability of end-to-end models, they are still restricted by certain input sequence length constraints and usually ignore the global context between events. To tackle this issue, we introduce a new global neural generation-based framework for document-level event argument extraction by constructing a document memory store to record the contextual event information and leveraging it to implicitly and explicitly help with decoding of arguments for later events. Empirical results show that our framework outperforms prior methods substantially and it is more robust to adversarially annotated examples with our constrained decoding design. (Our code and resources are available at https://github.com/xinyadu/memory_docie for research purpose.)

Deep Neural Networks (DNNs) have become an essential component in many application domains including web-based services. A variety of these services require high throughput and (close to) real-time features, for instance, to respond or react to users' requests or to process a stream of incoming data on time. However, the trend in DNN design is toward larger models with many layers and parameters to achieve more accurate results. Although these models are often pre-trained, the computational complexity in such large models can still be relatively significant, hindering low inference latency. Implementing a caching mechanism is a typical systems engineering solution for speeding up a service response time. However, traditional caching is often not suitable for DNN-based services. In this paper, we propose an end-to-end automated solution to improve the performance of DNN-based services in terms of their computational complexity and inference latency. Our caching method adopts the ideas of self-distillation of DNN models and early exits. The proposed solution is an automated online layer caching mechanism that allows early exiting of a large model during inference time if the cache model in one of the early exits is confident enough for final prediction. One of the main contributions of this paper is that we have implemented the idea as an online caching, meaning that the cache models do not need access to training data and perform solely based on the incoming data at run-time, making it suitable for applications using pre-trained models. Our experiments results on two downstream tasks (face and object classification) show that, on average, caching can reduce the computational complexity of those services up to 58\% (in terms of FLOPs count) and improve their inference latency up to 46\% with low to zero reduction in accuracy.

With the recent growth in computer vision applications, the question of how fair and unbiased they are has yet to be explored. There is abundant evidence that the bias present in training data is reflected in the models, or even amplified. Many previous methods for image dataset de-biasing, including models based on augmenting datasets, are computationally expensive to implement. In this study, we present a fast and effective model to de-bias an image dataset through reconstruction and minimizing the statistical dependence between intended variables. Our architecture includes a U-net to reconstruct images, combined with a pre-trained classifier which penalizes the statistical dependence between target attribute and the protected attribute. We evaluate our proposed model on CelebA dataset, compare the results with a state-of-the-art de-biasing method, and show that the model achieves a promising fairness-accuracy combination.

A large body of work shows that machine learning (ML) models can leak sensitive or confidential information about their training data. Recently, leakage due to distribution inference (or property inference) attacks is gaining attention. In this attack, the goal of an adversary is to infer distributional information about the training data. So far, research on distribution inference has focused on demonstrating successful attacks, with little attention given to identifying the potential causes of the leakage and to proposing mitigations. To bridge this gap, as our main contribution, we theoretically and empirically analyze the sources of information leakage that allows an adversary to perpetrate distribution inference attacks. We identify three sources of leakage: (1) memorizing specific information about the $\mathbb{E}[Y|X]$ (expected label given the feature values) of interest to the adversary, (2) wrong inductive bias of the model, and (3) finiteness of the training data. Next, based on our analysis, we propose principled mitigation techniques against distribution inference attacks. Specifically, we demonstrate that causal learning techniques are more resilient to a particular type of distribution inference risk termed distributional membership inference than associative learning methods. And lastly, we present a formalization of distribution inference that allows for reasoning about more general adversaries than was previously possible.

Ontology is a popular method for knowledge representation in different domains, including the legal domain, and description logics (DL) is commonly used as its description language. To handle reasoning based on inconsistent DL-based legal ontologies, the current paper presents a structured argumentation framework particularly for reasoning in legal contexts on the basis of ASPIC+, and translates the legal ontology into formulas and rules of an argumentation theory. With a particular focus on the design of autonomous vehicles from the perspective of legal AI, we show that using this combined theory of formal argumentation and DL-based legal ontology, acceptable assertions can be obtained based on inconsistent ontologies, and the traditional reasoning tasks of DL ontologies can also be accomplished. In addition, a formal definition of explanations for the result of reasoning is presented.

For best-in-class artificial intelligence solutions to actually earn that designation, Sindhu Joseph warns that the tools can't be used as "set it and forget it." Joseph, the co-founder and CEO of CogniCor, a California-based developer of an AI-powered business automation platform, reminded those attending her panel on day two of the inaugural Future Proof festival of the massive failure that was Microsoft's Tay. In spring 2016, the AI chatbot, named as an acronym for "thinking about you," was launched and pulled within a day of operation. Its machine-learning capabilities had caused it to spew racist, misogynistic and anti-semitic statements across Twitter, in a spectacular public display of garbage in, garbage out. Just "letting the machine run" without proper human guidance or care is a huge pitfall, said Joseph, who holds a PhD in artificial intelligence and is the inventor of six patents related to the technology. "There's a lot of applications where that works really well.

"Is AI Coming For Commercial Art?" rendered by Stable Diffusion, prompted by Rob Salkowitz Earlier this summer, a piece generated by an AI text-to-image application won a prize in a state fair art competition, prying open a Pandora's Box of issues about the encroachment of technology into the domain of human creativity and the nature of art itself. As fascinating as those questions are, the rise of AI-based image tools like Dall-E, Midjourney and Stable Diffusion, which rapidly generate detailed and beautiful images based on text descriptions supplied by the user, pose a much more practical and immediate concern: They could very well hold a shiny, photorealistically-rendered dagger to the throats of hundreds of thousands of commercial artists working in the entertainment, videogame, advertising and publishing industries, according to a number of professionals who have worked with the technology. How impactful would this be to the global creative economy that runs on spectacular imagery? Think about the 10 minutes of credits at the end of every modern Hollywood blockbuster. Same with videogames, where commercial artists hone their skills for years to score plum jobs like concept artist and character designer.

Role requiring'No experience data provided' months of experience in None Role requiring'No experience data provided' months of experience in None Events in recent years have made us all too familiar with the havoc that natural disasters can wreak, and the increasing frequency and intensity with which they are occurring. Despite record levels of losses, conventional methods of risk modeling continue to paint at best an incomplete picture of these threats. While AI alone may not be able to thwart these disasters, it can help us become more prepared for them, and ultimately that will lead to better outcomes. As a Senior Data Scientist – Computer Vision, you are comfortable and excited to work closely with the engineering team to build the best AI tech possible. You will scale the development of top-tier models by using diverse data sources to provide strong insights and maximize the impact of our company efforts.

Evident's game-changing technology enables the safe and private exchange of data to help businesses manage risk across their customers, employees and extended ecosystem, including vendors, partners, franchisees. The world's largest businesses rely on Evident to make fast and informed decisions as to who to allow into their ecosystem, by collecting, analyzing and making decisions based on sensitive identity and credentials information while protecting privacy and compliance. Our customers rely on Evident to enable them to operate and demonstrate compliance in the remote-first, ever-changing regulatory environment of the future. Underlying all of our solutions is our privacy-first secure enterprise platform, accessed via our web portal or API's, and providing a highly scalable and configurable solution to manage communications, storage, decisioning and ongoing monitoring of data subjects and credentials. Evident is a remote-first, VC-backed tech startup, headquartered in Atlanta, GA.

Were you unable to attend Transform 2022? Check out all of the summit sessions in our on-demand library now! Ironclad yesterday unveiled a new version of its contract platform embedded with an AI layer in an effort to improve business workflows throughout the lifecycle of a contract. Organizations can create contracts 60% faster by automating the contract creation process, according to Jason Boehmig, the company's CEO and co-founder. They will also have the capability to "slice and dice" all the operational data in previously executed contracts, he said.