Most sign language translation (SLT) methods to date require the use of gloss annotations to provide additional supervision information, however, the acquisition of gloss is not easy. To solve this problem, we first perform an analysis of existing models to confirm how gloss annotations make SLT easier. We find that it can provide two aspects of information for the model, 1) it can help the model implicitly learn the location of semantic boundaries in continuous sign language videos, 2) it can help the model understand the sign language video globally. We then propose \emph{gloss attention}, which enables the model to keep its attention within video segments that have the same semantics locally, just as gloss helps existing models do. Furthermore, we transfer the knowledge of sentence-to-sentence similarity from the natural language model to our gloss attention SLT network (GASLT) to help it understand sign language videos at the sentence level. Experimental results on multiple large-scale sign language datasets show that our proposed GASLT model significantly outperforms existing methods. Our code is provided in \url{https://github.com/YinAoXiong/GASLT}.

The representation learning of speech, without textual resources, is an area of significant interest for many low resource speech applications. In this paper, we describe an approach to self-supervised representation learning from raw audio using a hidden unit clustering (HUC) framework. The input to the model consists of audio samples that are windowed and processed with 1-D convolutional layers. The learned "time-frequency" representations from the convolutional neural network (CNN) module are further processed with long short term memory (LSTM) layers which generate a contextual vector representation for every windowed segment. The HUC framework, allowing the categorization of the representations into a small number of phoneme-like units, is used to train the model for learning semantically rich speech representations. The targets consist of phoneme-like pseudo labels for each audio segment and these are generated with an iterative k-means algorithm. We explore techniques that improve the speaker invariance of the learned representations and illustrate the effectiveness of the proposed approach on two settings, i) completely unsupervised speech applications on the sub-tasks described as part of the ZeroSpeech 2021 challenge and ii) semi-supervised automatic speech recognition (ASR) applications on the TIMIT dataset and on the GramVaani challenge Hindi dataset. In these experiments, we achieve state-of-art results for various ZeroSpeech tasks. Further, on the ASR experiments, the HUC representations are shown to improve significantly over other established benchmarks based on Wav2vec, HuBERT and Best-RQ.

Transformer-based pre-trained language models, such as BERT, achieve great success in various natural language understanding tasks. Prior research found that BERT captures a rich hierarchy of linguistic information at different layers. However, the vanilla BERT uses the same self-attention mechanism for each layer to model the different contextual features. In this paper, we propose a HybridBERT model which combines self-attention and pooling networks to encode different contextual features in each layer. Additionally, we propose a simple DropMask method to address the mismatch between pre-training and fine-tuning caused by excessive use of special mask tokens during Masked Language Modeling pre-training. Experiments show that HybridBERT outperforms BERT in pre-training with lower loss, faster training speed (8% relative), lower memory cost (13% relative), and also in transfer learning with 1.5% relative higher accuracies on downstream tasks. Additionally, DropMask improves accuracies of BERT on downstream tasks across various masking rates.

Sharing ideas through communication with peers is the primary mode of human interaction. Consequently, extensive research has been conducted in the area of conversational AI, leading to an increase in the availability and diversity of conversational tasks, datasets, and methods. However, with numerous tasks being explored simultaneously, the current landscape of conversational AI becomes fragmented. Therefore, initiating a well-thought-out model for a dialogue agent can pose significant challenges for a practitioner. Towards highlighting the critical ingredients needed for a practitioner to design a dialogue agent from scratch, the current study provides a comprehensive overview of the primary characteristics of a dialogue agent, the supporting tasks, their corresponding open-domain datasets, and the methods used to benchmark these datasets. We observe that different methods have been used to tackle distinct dialogue tasks. However, building separate models for each task is costly and does not leverage the correlation among the several tasks of a dialogue agent. As a result, recent trends suggest a shift towards building unified foundation models. To this end, we propose UNIT, a UNified dIalogue dataseT constructed from conversations of existing datasets for different dialogue tasks capturing the nuances for each of them. We also examine the evaluation strategies used to measure the performance of dialogue agents and highlight the scope for future research in the area of conversational AI.

Tensor networks, widely used for providing efficient representations of low-energy states of local quantum many-body systems, have been recently proposed as machine learning architectures which could present advantages with respect to traditional ones. In this work we show that tensor network architectures have especially prospective properties for privacy-preserving machine learning, which is important in tasks such as the processing of medical records. First, we describe a new privacy vulnerability that is present in feedforward neural networks, illustrating it in synthetic and real-world datasets. Then, we develop well-defined conditions to guarantee robustness to such vulnerability, which involve the characterization of models equivalent under gauge symmetry. We rigorously prove that such conditions are satisfied by tensor-network architectures. In doing so, we define a novel canonical form for matrix product states, which has a high degree of regularity and fixes the residual gauge that is left in the canonical forms based on singular value decompositions. We supplement the analytical findings with practical examples where matrix product states are trained on datasets of medical records, which show large reductions on the probability of an attacker extracting information about the training dataset from the model's parameters. Given the growing expertise in training tensor-network architectures, these results imply that one may not have to be forced to make a choice between accuracy in prediction and ensuring the privacy of the information processed.

São Paulo, Brazil – As the city of São Paulo prepares to roll out thousands of surveillance cameras with facial recognition, experts are raising concerns on the indiscriminate use of this technology in the Brazilian megalopolis could exacerbate problems such as structural racism and inequality, while also posing risks to data privacy and cybersecurity. The Smart Sampa project is the latest among a series of initiatives involving modern surveillance techniques in various Brazilian states. It is significant due to the sheer size of the population it will impact: São Paulo, the most populous city in the Southern Hemisphere, is home to 12 million people. The project aims to roll out a single video surveillance platform that integrates and supports the operations of emergency and traffic services, the city's public transport network, and police forces. By 2024, up to 20,000 cameras will be installed, and an equal number of third-party and private cameras will be integrated into the network.

The Perseverance Rover has found evidence of organic compounds in the Jezero Crater on Mars. Don't get too excited: These compounds could have also developed in nonbiological ways. But even if it's not proof of organic life on Mars, the results hint at complex organic conditions for the "key building blocks for life." Organic molecules like those observed in the Jezero Crater contain carbon and often hydrogen atoms. They're the core components of life as we know it on Earth.

Google's parent company has announced the rollout of its chatbot rival to ChatGPT in the European Union and Brazil, as tech firms ramp up their competition to dominate artificial intelligence. Bard is now available in 27 EU countries and Brazil, as well as 40 new languages, including Arabic, Chinese, German, Hindi and Spanish, Alphabet said on Thursday. "Curiosity and imagination are the driving forces behind human creativity," Bard's product lead Jack Krawczyk and vice president Amarnag Subramanya said in a blog post. "Whether it's a child inventing a game, friends dreaming up their next adventure, or an entrepreneur coming up with a new business idea, our ability to imagine new possibilities is one of our most innate human qualities. That's why we created Bard: to help you explore that curiosity, augment your imagination and ultimately get your ideas off the ground – not just by answering your questions, but by helping you build on them."

Google's Bard gained a handful of new features and functions Thursday in the chatbot AI's latest round of updates, including expanded linguistic knowledge, more nuanced response controls and the ability to respond with spoken word in addition to text. Users can now converse with the AI in Arabic, Chinese, German, Hindi and Spanish, among others as well as access the platform from more places on the planet, such as Brazil and "across Europe," Jack Krawczyk, Bard Product Lead, and Amarnag Subramanya, Bard's VP of Engineering, wrote in a blog post Thursday. "As we bring Bard to more regions and languages over time, we'll continue to use our AI Principles as a guide, incorporate user feedback, and take steps to protect people's privacy and data." Users will have the option to either read or listen to the AI's generated responses, which Krawczyk and Subramanya believe will help immensely when users want to hear the correct pronunciation of words in those 40 newly-added languages. Users have also been afforded more robust controls over how friendly Bard will be with five distinct options for the AI's tone: simple, long, short, professional or casual.

Fox News Washington-based correspondent Mark Meredith breaks down which jobs are most at risk during the AI revolution on'Special Report.' AI-powered chatbot tutors will likely revolutionize traditional education and benefit students with one-on-one training, according to a University of California, Berkeley professor of computer science. ChatGPT has already made its mark among students, as younger generations rushed to use the chatbot that can mimic human conversation when it was released last year. Berkeley professor and leading AI expert Stuart Russell speculates that as the technology evolves, it could revolutionize traditional education with ChatGPT-style personalized tutors. "Education is the biggest benefit that we can look for in the next few years," Russell told the Guardian of AI's potential impact on education.