A recent research line has obtained strong results on bilingual lexicon induction by aligning independently trained word embeddings in two languages and using the resulting cross-lingual embeddings to induce word translation pairs through nearest neighbor or related retrieval methods. In this paper, we propose an alternative approach to this problem that builds on the recent work on unsupervised machine translation. This way, instead of directly inducing a bilingual lexicon from cross-lingual embeddings, we use them to build a phrase-table, combine it with a language model, and use the resulting machine translation system to generate a synthetic parallel corpus, from which we extract the bilingual lexicon using statistical word alignment techniques. As such, our method can work with any word embedding and cross-lingual mapping technique, and it does not require any additional resource besides the monolingual corpus used to train the embeddings. When evaluated on the exact same cross-lingual embeddings, our proposed method obtains an average improvement of 6 accuracy points over nearest neighbor and 4 points over CSLS retrieval, establishing a new state-of-the-art in the standard MUSE dataset.

Automation of tasks can have critical consequences when humans lose agency over decision processes. Deep learning models are particularly susceptible since current black-box approaches lack explainable reasoning. We argue that both the visual interface and model structure of deep learning systems need to take into account interaction design. We propose a framework of collaborative semantic inference (CSI) for the co-design of interactions and models to enable visual collaboration between humans and algorithms. The approach exposes the intermediate reasoning process of models which allows semantic interactions with the visual metaphors of a problem, which means that a user can both understand and control parts of the model reasoning process. We demonstrate the feasibility of CSI with a co-designed case study of a document summarization system.

Answer Set Programming (ASP) is a well-known declarative formalism in logic programming. Efficient implementations made it possible to apply ASP in many scenarios, ranging from deductive databases applications to the solution of hard combinatorial problems. State-of-the-art ASP systems are based on the traditional ground\&solve approach and are general-purpose implementations, i.e., they are essentially built once for any kind of input program. In this paper, we propose an extended architecture for ASP systems, in which parts of the input program are compiled into an ad-hoc evaluation algorithm (i.e., we obtain a specific binary for a given program), and might not be subject to the grounding step. To this end, we identify a condition that allows the compilation of a sub-program, and present the related partial compilation technique. Importantly, we have implemented the new approach on top of a well-known ASP solver and conducted an experimental analysis on publicly-available benchmarks. Results show that our compilation-based approach improves on the state of the art in various scenarios, including cases in which the input program is stratified or the grounding blow-up makes the evaluation unpractical with traditional ASP systems.

Decision support systems (e.g., for ecological conservation) and autonomous systems (e.g., adaptive controllers in smart cities) start to be deployed in real applications. Although their operations often impact many users or stakeholders, no fairness consideration is generally taken into account in their design, which could lead to completely unfair outcomes for some users or stakeholders. To tackle this issue, we advocate for the use of social welfare functions that encode fairness and present this general novel problem in the context of (deep) reinforcement learning, although it could possibly be extended to other machine learning tasks.

If you make a purchase by clicking one of our links, we may earn a small share of the revenue. However, our picks and opinions are independent from USA Today's newsroom and any business incentives. Look, guys--I don't want to alarm you, but we're kind of in the middle of a savings bonanza right now. From Prime Day to Madewell's Very Rare sale, there are tons of retailers competing to gain your hard-earned bucks right now. And while usually I'm the type of shopper who gets horrified at the thought of spending more than $100 on something unless it's absolutely essential, even I'm getting in on the action (which should tell you something).

Three top executives at the Israeli start-up MDGo - Eli Zerah, Gilad Avrashi and Itay Bengad, pictured from left to right - are hoping to revolutionize how first responders dispatch to car crashes. Their technology applies artificial intelligence to car sensor data to try to predict what kind of injuries may have been sustained. That information is sent almost immediately to EMS before they arrive, company officials said. RTC Your car just flipped over and, hopefully, minutes later, an ambulance is racing to the scene. But how much will those emergency medical technicians actually know about your condition as they arrive?

Patrick Winston, a beloved professor and computer scientist at MIT, died on July 19 at Massachusetts General Hospital in Boston. A professor at MIT for almost 50 years, Winston was director of MIT's Artificial Intelligence Laboratory from 1972 to 1997 before it merged with the Laboratory for Computer Science to become MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL). A devoted teacher and cherished colleague, Winston led CSAIL's Genesis Group, which focused on developing AI systems that have human-like intelligence, including the ability to tell, perceive, and comprehend stories. He believed that such work could help illuminate aspects of human intelligence that scientists don't yet understand. "My principal interest is in figuring out what's going on inside our heads, and I'm convinced that one of the defining features of human intelligence is that we can understand stories,'" said Winston, the Ford Professor of Artificial Intelligence and Computer Science, in a 2011 interview for CSAIL.

My grandfather, a lover of classical music, was president of the Hull Philharmonic Orchestra for many years. When I was 15, I played him an orchestrated version of Nobuo Uematsu's To Zanarkand, from the video game Final Fantasy X. "This isn't real music if it's from a video game," he told me at the time. I don't think he could ever have imagined that 12 years later, the Hull orchestra to which he had devoted so many years would be performing music from 1980s video games, in front of a packed hall. In the past, video game music concerts were a promotional novelty, but today they are regular and well-attended billings in venues across the world. From The Legend of Zelda: Symphony of the Goddess to Final Fantasy: Distant Worlds, Assassin's Creed Symphony to the recent debut by the London Video Game Orchestra and even a performance by the BBC Concert Orchestra hosted by lauded composer Jessica Curry, fans are flocking to concert halls to hear their favourite video game melodies played live.

In this May 7, 2018, file photo Microsoft CEO Satya Nadella looks on during a video as he delivers the keynote address at Build, the company's annual conference for software developers in Seattle. Microsoft is paying more than $25 million to settle federal corruption charges involving a bribery scheme in its Hungary office and three other foreign subsidiaries, the U.S. Securities and Exchange Commission said Monday, July 22, 2019. NEW YORK – Microsoft is paying more than $25 million to settle federal corruption charges involving a bribery scheme in Hungary and other foreign offices. The U.S. Securities and Exchange Commission said Microsoft will pay about $16.6 million to settle charges that it violated the Foreign Corrupt Practices Act. While the case centered on Hungary, the SEC said it also found improprieties at Microsoft offices in Saudi Arabia, Thailand and Turkey.

Where Will Man Take Us? looks at the primary drivers of this change – artificial intelligence, bio-engineering and nanotechnology. It looks at how in our quest to bring human-like cognition to AI, we are forced to look at ourselves and answer some of our oldest questions – what is it to be human, what is self-awareness, what is consciousness. AI's ability to crunch data and math's ability to find patterns, could also help us unravel some of our greatest mysteries – astrology, aliens, the secret to unbroken eternal happiness. The book also looks at the advancements in genetics – the ability to edit the genome truly marks the beginning of man's next avatar. All of this is impacting some of our greatest ideas and institutions.