Task-oriented dialogue systems (TODS) are continuing to rise in popularity as various industries find ways to effectively harness their capabilities, saving both time and money. However, even state-of-the-art TODS are not yet reaching their full potential. TODS typically have a primary design focus on completing the task at hand, so the metric of task-resolution should take priority. Other conversational quality attributes that may point to the success, or otherwise, of the dialogue, may be ignored. This can cause interactions between human and dialogue system that leave the user dissatisfied or frustrated. This paper explores the literature on evaluative frameworks of dialogue systems and the role of conversational quality attributes in dialogue systems, looking at if, how, and where they are utilised, and examining their correlation with the performance of the dialogue system.

The Morrison Government is investing $12 million to strengthen partnerships between the technology sector and regional Australians to solve uniquely Australian challenges. The new Catalysing the Artificial Intelligence Opportunity in Our Regions program will provide competitive grant funding over three rounds to regional organisations for artificial intelligence (AI) projects that deliver benefits to regional industries, businesses and communities. The program is part of the Government's $124.1 million investment under the AI Action Plan, which sets out a vision for Australia to become a global leader in developing and adopting trusted, secure and responsible artificial intelligence. Under round one, grants of between $250,000 and $500,000 are available. Minister for Science and Technology Melissa Price said the program would showcase the opportunities for AI to boost regional capabilities, grow trust in this technology and create a pathway for high-skilled jobs in regional Australia.

Dec 20 (Thomson Reuters Foundation) -Two days after it was sued by Rohingya refugees from Myanmar over allegations that it did not take action against hate speech, social media company Meta, formerly known as Facebook, announced a new artificial intelligence system to tackle harmful content. Machine learning tools have increasingly become the go-to solution for tech firms to police their platforms, but questions have been raised about their accuracy and their potential threat to freedom of speech. WHY ARE SOCIAL MEDIA FIRMS UNDER FIRE OVER CONTENT MODERATION? The $150 billion Rohingya class-action lawsuit filed this month came at the end of a tumultuous period for social media giants, which have been criticised for failing to effectively tackle hate speech online and increasing polarization. The complaint argues that calls for violence shared on Facebook contributed to real-world violence against the Rohingya community, which suffered a military crackdown in 2017 that refugees said included mass killings and rape.

As a lover of tough single player games, I’m quite accustomed to getting my butt handed to me by AI, and usually not even a real one. I also happen to be the owner of a full sized human brain, and though it’s not without its problems, its ability to learn and change is usually why I eventually overcome those difficult in game challenges.So when I read about a few human brain cells in a petri dish that are already performing much better at a videogame than AI can, it’s concerning to me and my gaming future. New Scientist reports that a team in Australia has been growing these small puddles of brain and now one has learnt to play Pong, in fairly impressive time.Cortical labs is a company working on integrating biological neurons with your more traditional silicon based computing hardware. They grow brain cells on microelectronic arrays, so the cells can be stimulated. These hybrid chips are said to be able to learn and restructure themselves to get past problems, like stopping a sneaky ball that wants in your goal.According to Cortical labs, AIs typically take 90 minutes to learn Pong, whereas this ‘DishBrain’ (yes, that’s what it’s called) managed to have it down in five. Though the researchers do note that a good AI would still absolutely demolish the cells, once both properly trained. 

AI connects your brand with the world's leading executives in the fields of AI strategy, machine learning and digitally disruptive technologies – thought leaders and innovators driving this pioneering sector. We are the trusted authority at the cutting-edge of developments in artificial intelligence, machine learning and automation; guiding the business leaders, influencers and disruptors that are shaping the industry.

GENEVA – Japan, the United States and other countries have blocked any advancement in U.N. talks toward legally binding measures to ban and regulate the development and use of lethal autonomous weapon systems. The Sixth Review Conference of the Convention on Certain Conventional Weapons ended Friday in Geneva without progress, failing to reflect eight years of work and leaving countries and nongovernmental organizations that have called for legally binding rules expressing disappointment. Also referred to as "killer robots," autonomous weapons are artificial intelligence-powered weapons using facial recognition and algorithms. Once activated, the weapons can select and attack targets without the assistance of a human operator. They pose ethical, legal and security risks.

In video reviews of the latest drone models to his 80,000 YouTube subscribers, Indiana college student Carson Miller doesn't seem like an unwitting tool of Chinese spies. Yet that's how the U.S. is increasingly viewing him and thousands of other Americans who purchase drones built by Shenzhen-based SZ DJI Technology Co., the world's top producer of unmanned aerial vehicles. Miller, who bought his first DJI model in 2016 for $500 and now owns six of them, shows why the company controls more than half of the U.S. drone market. "If tomorrow DJI were completely banned," the 21-year-old said, "I would be pretty frightened." Critics of DJI warn the dronemaker may be channeling reams of sensitive data to Chinese intelligence agencies on everything from critical infrastructure like bridges and dams to personal information such as heart rates and facial recognition.

Real-world networks often come with side information that can help to improve the performance of network analysis tasks such as clustering. Despite a large number of empirical and theoretical studies conducted on network clustering methods during the past decade, the added value of side information and the methods used to incorporate it optimally in clustering algorithms are relatively less understood. We propose a new iterative algorithm to cluster networks with side information for nodes (in the form of covariates) and show that our algorithm is optimal under the Contextual Symmetric Stochastic Block Model. Our algorithm can be applied to general Contextual Stochastic Block Models and avoids hyperparameter tuning in contrast to previously proposed methods. We confirm our theoretical results on synthetic data experiments where our algorithm significantly outperforms other methods, and show that it can also be applied to signed graphs. Finally we demonstrate the practical interest of our method on real data.

In programming, learning code representations has a variety of applications, including code classification, code search, comment generation, bug prediction, and so on. Various representations of code in terms of tokens, syntax trees, dependency graphs, code navigation paths, or a combination of their variants have been proposed, however, existing vanilla learning techniques have a major limitation in robustness, i.e., it is easy for the models to make incorrect predictions when the inputs are altered in a subtle way. To enhance the robustness, existing approaches focus on recognizing adversarial samples rather than on the valid samples that fall outside a given distribution, which we refer to as out-of-distribution (OOD) samples. Recognizing such OOD samples is the novel problem investigated in this paper. To this end, we propose to first augment the in=distribution datasets with out-of-distribution samples such that, when trained together, they will enhance the model's robustness. We propose the use of an energy-bounded learning objective function to assign a higher score to in-distribution samples and a lower score to out-of-distribution samples in order to incorporate such out-of-distribution samples into the training process of source code models. In terms of OOD detection and adversarial samples detection, our evaluation results demonstrate a greater robustness for existing source code models to become more accurate at recognizing OOD data while being more resistant to adversarial attacks at the same time. Furthermore, the proposed energy-bounded score outperforms all existing OOD detection scores by a large margin, including the softmax confidence score, the Mahalanobis score, and ODIN.

Large-scale autoregressive language models such as GPT-3 are few-shot learners that can perform a wide range of language tasks without fine-tuning. While these models are known to be able to jointly represent many different languages, their training data is dominated by English, potentially limiting their cross-lingual generalization. In this work, we train multilingual autoregressive language models on a balanced corpus covering a diverse set of languages, and study their few- and zero-shot learning capabilities in a wide range of tasks. Our largest model with 7.5 billion parameters sets new state of the art in few-shot learning in more than 20 representative languages, outperforming GPT-3 of comparable size in multilingual commonsense reasoning (with +7.4% absolute accuracy improvement in 0-shot settings and +9.4% in 4-shot settings) and natural language inference (+5.4% in each of 0-shot and 4-shot settings). On the FLORES-101 machine translation benchmark, our model outperforms GPT-3 on 171 out of 182 translation directions with 32 training examples, while surpassing the official supervised baseline in 45 directions. We present a detailed analysis of where the model succeeds and fails, showing in particular that it enables cross-lingual in-context learning on some tasks, while there is still room for improvement on surface form robustness and adaptation to tasks that do not have a natural cloze form. Finally, we evaluate our models in social value tasks such as hate speech detection in five languages and find it has limitations similar to comparable sized GPT-3 models.