Semantic role labeling (SRL) identifies the predicate-argument structure in a sentence. This task is usually accomplished in four steps: predicate identification, predicate sense disambiguation, argument identification, and argument classification. Errors introduced at one step propagate to later steps. Unfortunately, the existing SRL evaluation scripts do not consider the full effect of this error propagation aspect. They either evaluate arguments independent of predicate sense (CoNLL09) or do not evaluate predicate sense at all (CoNLL05), yielding an inaccurate SRL model performance on the argument classification task. In this paper, we address key practical issues with existing evaluation scripts and propose a more strict SRL evaluation metric PriMeSRL. We observe that by employing PriMeSRL, the quality evaluation of all SoTA SRL models drops significantly, and their relative rankings also change. We also show that PriMeSRLsuccessfully penalizes actual failures in SoTA SRL models.

With the rapid spread of COVID-19 worldwide, viral genomic data is available in the order of millions of sequences on public databases such as GISAID. This Big Data creates a unique opportunity for analysis towards the research of effective vaccine development for current pandemics, and avoiding or mitigating future pandemics. One piece of information that comes with every such viral sequence is the geographical location where it was collected -- the patterns found between viral variants and geographical location surely being an important part of this analysis. One major challenge that researchers face is processing such huge, highly dimensional data to obtain useful insights as quickly as possible. Most of the existing methods face scalability issues when dealing with the magnitude of such data. In this paper, we propose an approach that first computes a numerical representation of the spike protein sequence of SARS-CoV-2 using $k$-mers (substrings) and then uses several machine learning models to classify the sequences based on geographical location. We show that our proposed model significantly outperforms the baselines. We also show the importance of different amino acids in the spike sequences by computing the information gain corresponding to the true class labels.

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control, and understanding downstream task performance in Natural Language Processing. The connection points between disentanglement and downstream tasks, however, remains underexplored from a explanatory standpoint. This work presents a methodology for assessment of geometrical properties of the resulting latent space w.r.t. vector operations and semantic disentanglement in quantitative and qualitative terms, based on a VAE-based supervised framework. Empirical results indicate that the role-contents of explanations, such as \textit{ARG0-animal}, are disentangled in the latent space, which provides us a chance for controlling the explanation generation by manipulating the traversal of vector over latent space.

Visually grounded speech (VGS) models are trained on images paired with unlabelled spoken captions. Such models could be used to build speech systems in settings where it is impossible to get labelled data, e.g. for documenting unwritten languages. However, most VGS studies are in English or other high-resource languages. This paper attempts to address this shortcoming. We collect and release a new single-speaker dataset of audio captions for 6k Flickr images in Yor\`ub\'a -- a real low-resource language spoken in Nigeria. We train an attention-based VGS model where images are automatically tagged with English visual labels and paired with Yor\`ub\'a utterances. This enables cross-lingual keyword localisation: a written English query is detected and located in Yor\`ub\'a speech. To quantify the effect of the smaller dataset, we compare to English systems trained on similar and more data. We hope that this new dataset will stimulate research in the use of VGS models for real low-resource languages.

Well-designed diagnostic tasks have played a key role in studying the failure of neural nets (NNs) to generalize systematically. Famous examples include SCAN and Compositional Table Lookup (CTL). Here we introduce CTL++, a new diagnostic dataset based on compositions of unary symbolic functions. While the original CTL is used to test length generalization or productivity, CTL++ is designed to test systematicity of NNs, that is, their capability to generalize to unseen compositions of known functions. CTL++ splits functions into groups and tests performance on group elements composed in a way not seen during training. We show that recent CTL-solving Transformer variants fail on CTL++. The simplicity of the task design allows for fine-grained control of task difficulty, as well as many insightful analyses. For example, we measure how much overlap between groups is needed by tested NNs for learning to compose. We also visualize how learned symbol representations in outputs of functions from different groups are compatible in case of success but not in case of failure. These results provide insights into failure cases reported on more complex compositions in the natural language domain. Our code is public.

The COVID-19 pandemic has affected countries across the world, demanding drastic public health policies to mitigate the spread of infection, leading to economic crisis as a collateral damage. In this work, we investigated the impact of human mobility (described via international commercial flights) on COVID-19 infection dynamics at the global scale. For this, we developed a graph neural network-based framework referred to as Dynamic Connectivity GraphSAGE (DCSAGE), which operates over spatiotemporal graphs and is well-suited for dynamically changing adjacency information. To obtain insights on the relative impact of different geographical locations, due to their associated air traffic, on the evolution of the pandemic, we conducted local sensitivity analysis on our model through node perturbation experiments. From our analyses, we identified Western Europe, North America, and Middle East as the leading geographical locations fueling the pandemic, attributed to the enormity of air traffic originating or transiting through these regions. We used these observations to identify tangible air traffic reduction strategies that can have a high impact on controlling the pandemic, with minimal interference to human mobility. Our work provides a robust deep learning-based tool to study global pandemics and is of key relevance to policy makers to take informed decisions regarding air traffic restrictions during future outbreaks.

Several biomedical language models have already been developed for clinical language inference. However, these models typically utilize general vocabularies and are trained on relatively small clinical corpora. We sought to evaluate the impact of using a domain-specific vocabulary and a large clinical training corpus on the performance of these language models in clinical language inference. We trained a Bidirectional Encoder Decoder from Transformers (BERT) model using a diverse, deidentified corpus of 75 million deidentified clinical notes authored at the University of California, San Francisco (UCSF). We evaluated this model on several clinical language inference benchmark tasks: clinical and temporal concept recognition, relation extraction and medical language inference. We also evaluated our model on two tasks using discharge summaries from UCSF: diagnostic code assignment and therapeutic class inference. Our model performs at par with the best publicly available biomedical language models of comparable sizes on the public benchmark tasks, and is significantly better than these models in a within-system evaluation on the two tasks using UCSF data. The use of in-domain vocabulary appears to improve the encoding of longer documents. The use of large clinical corpora appears to enhance document encoding and inferential accuracy. However, further research is needed to improve abbreviation resolution, and numerical, temporal, and implicitly causal inference.

Rendering to their abilities to provide ubiquitous connectivity, flexibly and cost effectively, unmanned aerial vehicles (UAVs) have been getting more and more research attention. To take the UAVs' performance to the next level, however, they need to be merged with some other technologies like non-orthogonal multiple access (NOMA) and millimeter wave (mmWave), which both promise high spectral efficiency (SE). As managing UAVs efficiently may not be possible using model-based techniques, another key innovative technology that UAVs will inevitably need to leverage is artificial intelligence (AI). Designing an AI-based technique that adaptively allocates radio resources and places UAVs in 3D space to meet certain communication objectives, however, is a tough row to hoe. In this paper, we propose a neuroevolution of augmenting topologies NEAT framework, referred to as ProSky, to manage NOMA-mmWave-UAV networks. ProSky exhibits a remarkable performance improvement over a model-based method. Moreover, ProSky learns 5.3 times faster than and outperforms, in both SE and energy efficiency EE while being reasonably fair, a deep reinforcement learning DRL based scheme. The ProSky source code is accessible to use here: https://github.com/Fouzibenfaid/ProSky

A British humanoid called Ai-Da has made history by becoming the first robot to speak at the House of Lords. Addressing members of the House of Lords Communications and Digital Committee on Tuesday afternoon, the bot spoke about whether creativity is under attack from AI and technology. When asked: 'How do you produce art and how is this different to what human artists produce?', Ai-Da replied: 'I could use my paintings by cameras in my eyes, my AI algorithms and my robotic arm to paint on canvas, which result in visually appealing images. 'For my poetry using neutral networks, this involves analysing a large corpus of text to identify common content and poetic structures, and then using these structures/content to generate new poems. 'How this differs to humans is consciousness.

Silent Eight announced an extension to its existing partnership with HSBC to tackle financial crime. The new service will cover the deployment of Negative News Screening that leverages machine learning to identify individuals who pose a greater risk for money laundering, fraud or terrorist financing. As financial crime continues to present a challenge, banks need to pivot to an increased use of Machine Learning within compliance, and move away from manual processes or alert scoring. Silent Eights' solution provides a more effective approach to address true matches and resolve the issue of false identifications. With this expansion, Silent Eight will be solving name screening matches across every risk type within HSBC.