Language is our lifeline to the world. But because high-quality translation tools don't exist for hundreds of languages, billions of people today can't access digital content or participate fully in conversations and communities online in their preferred or native languages. This is particularly an issue for hundreds of millions of people who speak the many languages of Africa and Asia. To help people connect better today and be part of the metaverse of tomorrow, our AI researchers created No Language Left Behind (NLLB), an effort to develop high-quality machine translation capabilities for most of the world's languages. Today, we're announcing an important breakthrough in NLLB: We've built a single AI model called NLLB-200, which translates 200 different languages with results far more accurate than what previous technology could accomplish.

We study federated contextual linear bandits, where $M$ agents cooperate with each other to solve a global contextual linear bandit problem with the help of a central server. We consider the asynchronous setting, where all agents work independently and the communication between one agent and the server will not trigger other agents' communication. We propose a simple algorithm named \texttt{FedLinUCB} based on the principle of optimism. We prove that the regret of \texttt{FedLinUCB} is bounded by $\tilde{O}(d\sqrt{\sum_{m=1}^M T_m})$ and the communication complexity is $\tilde{O}(dM^2)$, where $d$ is the dimension of the contextual vector and $T_m$ is the total number of interactions with the environment by $m$-th agent. To the best of our knowledge, this is the first provably efficient algorithm that allows fully asynchronous communication for federated contextual linear bandits, while achieving the same regret guarantee as in the single-agent setting.

High-order interaction events are common in real-world applications. Learning embeddings that encode the complex relationships of the participants from these events is of great importance in knowledge mining and predictive tasks. Despite the success of existing approaches, e.g. Poisson tensor factorization, they ignore the sparse structure underlying the data, namely the occurred interactions are far less than the possible interactions among all the participants. In this paper, we propose Nonparametric Embeddings of Sparse High-order interaction events (NESH). We hybridize a sparse hypergraph (tensor) process and a matrix Gaussian process to capture both the asymptotic structural sparsity within the interactions and nonlinear temporal relationships between the participants. We prove strong asymptotic bounds (including both a lower and an upper bound) of the sparsity ratio, which reveals the asymptotic properties of the sampled structure. We use batch-normalization, stick-breaking construction, and sparse variational GP approximations to develop an efficient, scalable model inference algorithm. We demonstrate the advantage of our approach in several real-world applications.

Few-shot recognition involves training an image classifier to distinguish novel concepts at test time using few examples (shot). Existing approaches generally assume that the shot number at test time is known in advance. This is not realistic, and the performance of a popular and foundational method has been shown to suffer when train and test shots do not match. We conduct a systematic empirical study of this phenomenon. In line with prior work, we find that shot sensitivity is broadly present across metric-based few-shot learners, but in contrast to prior work, larger neural architectures provide a degree of built-in robustness to varying test shot. More importantly, a simple, previously known but greatly overlooked class of approaches based on cosine distance consistently and greatly improves robustness to shot variation, by removing sensitivity to sample noise. We derive cosine alternatives to popular and recent few-shot classifiers, broadening their applicability to realistic settings. These cosine models consistently improve shot-robustness, outperform prior shot-robust state of the art, and provide competitive accuracy on a range of benchmarks and architectures, including notable gains in the very-low-shot regime.

In this work, we present a multi-modal model for commercial product classification, that combines features extracted by multiple neural network models from textual (CamemBERT and FlauBERT) and visual data (SE-ResNeXt-50), using simple fusion techniques. The proposed method significantly outperformed the unimodal models' performance and the reported performance of similar models on our specific task. We did experiments with multiple fusing techniques and found, that the best performing technique to combine the individual embedding of the unimodal network is based on combining concatenation and averaging the feature vectors. Each modality complemented the shortcomings of the other modalities, demonstrating that increasing the number of modalities can be an effective method for improving the performance of multi-label and multimodal classification problems.

Mental health disorders may cause severe consequences on all the countries' economies and health. For example, the impacts of the COVID-19 pandemic, such as isolation and travel ban, can make us feel depressed. Identifying early signs of mental health disorders is vital. For example, depression may increase an individual's risk of suicide. The state-of-the-art research in identifying mental disorder patterns from textual data, uses hand-labelled training sets, especially when a domain expert's knowledge is required to analyse various symptoms. This task could be time-consuming and expensive. To address this challenge, in this paper, we study and analyse the various clinical and non-clinical approaches to identifying mental health disorders. We leverage the domain knowledge and expertise in cognitive science to build a domain-specific Knowledge Base (KB) for the mental health disorder concepts and patterns. We present a weaker form of supervision by facilitating the generating of training data from a domain-specific Knowledge Base (KB). We adopt a typical scenario for analysing social media to identify major depressive disorder symptoms from the textual content generated by social users. We use this scenario to evaluate how our knowledge-based approach significantly improves the quality of results.

In this study, we propose feature extraction for multimodal meme classification using Deep Learning approaches. A meme is usually a photo or video with text shared by the young generation on social media platforms that expresses a culturally relevant idea. Since they are an efficient way to express emotions and feelings, a good classifier that can classify the sentiment behind the meme is important. To make the learning process more efficient, reduce the likelihood of overfitting, and improve the generalizability of the model, one needs a good approach for joint feature extraction from all modalities. In this work, we proposed to use different multimodal neural network approaches for multimodal feature extraction and use the extracted features to train a classifier to identify the sentiment in a meme.

A declarative action model is a compact representation of the state transitions of dynamic systems that generalizes over world objects. The specification of declarative action models is often a complex hand-crafted task. In this paper we formulate declarative action models via state constraints, and present the learning of such models as a combinatorial search. The comprehensive framework presented here allows us to connect the learning of declarative action models to well-known problem solving tasks. In addition, our framework allows us to characterize the existing work in the literature according to four dimensions: (1) the target action models, in terms of the state transitions they define; (2) the available learning examples; (3) the functions used to guide the learning process, and to evaluate the quality of the learned action models; (4) the learning algorithm. Last, the paper lists relevant successful applications of the learning of declarative actions models and discusses some open challenges with the aim of encouraging future research work.

The smallest mention of a heatwave in the UK leads to ice creams selling out, barbecues heating up and shorts being dusted off as the nation celebrates. In June this year, air temperatures in parts of the country soared to over 90 F (33 C), while sharp increases were also felt across Europe, the US and Asia. Air temperatures were recorded in excess of 18 F (10 C) above the average for the time of year in many cities, according to the World Meteorological Organisation. But new heat maps released by the European Space Agency (ESA) show that this might not be such a cause for celebration. They reveal that heat dissipated more slowly in urban areas creating'heat islands' and make life more of a struggle. Experts are worried that this effect will only be exacerbated as climate change continues to take hold.

More than 7,000 languages are currently spoken on this planet and Meta seemingly wants to understand them all. Six months ago, the company launched its ambitious No Language Left Behind (NLLB) project, training AI to translate seamlessly between numerous languages without having to go through English first. On Wednesday, the company announced its first big success, dubbed NLLB-200. It's an AI model that can speak in 200 tongues, including a number of less-widely spoken languages from across Asia and Africa, like Lao and Kamba. According to a Wednesday blog post from the company, NLLB-200 can translate 55 African languages with "high-quality results."