We introduce the task of entity-centric query refinement. Given an input query whose answer is a (potentially large) collection of entities, the task output is a small set of query refinements meant to assist the user in efficient domain exploration and entity discovery. We propose a method to create a training dataset for this task. For a given input query, we use an existing knowledge base taxonomy as a source of candidate query refinements, and choose a final set of refinements from among these candidates using a search procedure designed to partition the set of entities answering the input query. We demonstrate that our approach identifies refinement sets which human annotators judge to be interesting, comprehensive, and non-redundant. In addition, we find that a text generation model trained on our newly-constructed dataset is able to offer refinements for novel queries not covered by an existing taxonomy. Our code and data are available at https://github.

With the booming growth of advanced digital technologies, it has become possible for users as well as distributors of energy to obtain detailed and timely information about the electricity consumption of households. These technologies can also be used to forecast the household's electricity consumption (a.k.a. the load). In this paper, we investigate the use of Variational Mode Decomposition and deep learning techniques to improve the accuracy of the load forecasting problem. Although this problem has been studied in the literature, selecting an appropriate decomposition level and a deep learning technique providing better forecasting performance have garnered comparatively less attention. This study bridges this gap by studying the effect of six decomposition levels and five distinct deep learning networks. The raw load profiles are first decomposed into intrinsic mode functions using the Variational Mode Decomposition in order to mitigate their non-stationary aspect. Then, day, hour, and past electricity consumption data are fed as a three-dimensional input sequence to a four-level Wavelet Decomposition Network model. Finally, the forecast sequences related to the different intrinsic mode functions are combined to form the aggregate forecast sequence. The proposed method was assessed using load profiles of five Moroccan households from the Moroccan buildings' electricity consumption dataset (MORED) and was benchmarked against state-of-the-art time-series models and a baseline persistence model.

Document-level information extraction (IE) tasks have recently begun to be revisited in earnest using the end-to-end neural network techniques that have been successful on their sentence-level IE counterparts. Evaluation of the approaches, however, has been limited in a number of dimensions. In particular, the precision/recall/F1 scores typically reported provide few insights on the range of errors the models make. We build on the work of Kummerfeld and Klein (2013) to propose a transformation-based framework for automating error analysis in document-level event and (N-ary) relation extraction. We employ our framework to compare two state-of-the-art document-level template-filling approaches on datasets from three domains; and then, to gauge progress in IE since its inception 30 years ago, vs. four systems from the MUC-4 (1992) evaluation.

Neural Ordinary Differential Equations (Neural ODEs) are the continuous analog of Residual Neural Networks (ResNets). We investigate whether the discrete dynamics defined by a ResNet are close to the continuous one of a Neural ODE. We first quantify the distance between the ResNet's hidden state trajectory and the solution of its corresponding Neural ODE. Our bound is tight and, on the negative side, does not go to 0 with depth N if the residual functions are not smooth with depth. On the positive side, we show that this smoothness is preserved by gradient descent for a ResNet with linear residual functions and small enough initial loss. It ensures an implicit regularization towards a limit Neural ODE at rate 1 over N, uniformly with depth and optimization time. As a byproduct of our analysis, we consider the use of a memory-free discrete adjoint method to train a ResNet by recovering the activations on the fly through a backward pass of the network, and show that this method theoretically succeeds at large depth if the residual functions are Lipschitz with the input. We then show that Heun's method, a second order ODE integration scheme, allows for better gradient estimation with the adjoint method when the residual functions are smooth with depth. We experimentally validate that our adjoint method succeeds at large depth, and that Heun method needs fewer layers to succeed. We finally use the adjoint method successfully for fine-tuning very deep ResNets without memory consumption in the residual layers.

At ICRA 2022, Benjamin Rosman delivered a keynote presentation on an organization he co-founded called "Deep learning Indaba". Deep Learning Indaba is based in South Africa and their mission is to strengthen Artificial Intelligence and Machine Learning communities across Africa. They host yearly meetups in varying countries on the continent, as well as promote grass roots communities in each of the countries to run their own local events. An indaba is a Zulu word for a gathering or meeting. Such meetings are held throughout southern Africa, and serve several functions: to listen and share news of members of the community, to discuss common interests and issues facing the community, and to give advice and coach others.

Tehran, Iran – The United Kingdom's defence ministry has backed a Ukrainian claim that Ukraine's forces likely shot down an Iranian-made drone that was used by Russia in its offensive against its neighbouring country. In its latest military intelligence update on Wednesday, the ministry said it was "highly likely" that Russia has deployed unmanned aerial vehicles (UAV) made by Iran in the nearly seven-month war in Ukraine. "Russia is almost certainly increasingly sourcing weaponry from other heavily sanctioned states like Iran and North Korea as its own stocks dwindle," it said. The statement came a day after the Ukrainian military published several images and said it had likely shot down a drone near Kupiansk in Kharkiv that appeared to be an Iranian Shahed-136 model. The Iranian government has yet to comment on the claims, but its officials have previously denied supplying Russia with drones to be used in Ukraine, saying Iran would not assist either side in the war as it backed its resolution through dialogue. There are no known official specifications for the Shahed-136, but it is a so-called "suicide drone" that is capable of carrying a warhead over long distances.

An artificial intelligence (AI) system detects tuberculosis (TB) in chest X-rays at a level comparable to radiologists, according to a study published in Radiology. Researchers said the AI system may be able to aid screening in areas with limited radiologist resources. TB is an infectious disease of the lungs that kills more than a million people worldwide every year. The COVID-19 pandemic has exacerbated the problem, with recent reports indicating that 21% fewer people received care for TB in 2020 than in 2019. Almost 90% of the active TB infections occur in about 30 countries, many with scarce resources needed to address this public health problem.

Researchers have found that an artificial intelligence system is at least as good as human radiologists at identifying tuberculosis from chest X-rays, opening up its use for low-resource countries. Indeed, the deep learning program was superior in sensitivity and noninferior in specificity in identifying active pulmonary TB in frontal chest radiographs when compared with nine radiologists from India. The system could have particular value in low-income countries where large-scale screening programs are not always feasible due to cost and radiologist availability. Simulations revealed that using the deep learning system to identify likely TB-positive chest radiographs for confirmation using nucleic acid amplification testing (NAAT) reduced costs by between 40 and 80 percent per positive patient detected. "We hope this can be a tool used by non-expert physicians and healthcare workers to screen people en masse and get them to treatment where required without getting specialist doctors, who are in short supply,' said researcher Rory Pilgrim, a product manager at Google Health AI in Mountain View, California. "We believe we can do this with the people on the ground in a low-cost, high-volume way." The research is published in Radiology, a journal of the Radiological Society of North America. The deep-learning system was trained using 165,754 images from 22,284 individuals, nearly all from South Africa, and then tested using data from five countries. The total test set had 1236 images, of which 212 were identified as positive for TB based on microbiological tests or NAAT. These were binary scored by 10 radiologists from India and five from the USA, although one of the Indian radiologists was removed due to their much lower specificity than the others. Among 1236 test individuals assessed, the deep learning system achieved superior sensitivity compared with a prespecified analysis involving the nine radiologists from India, at 88% versus 75%, with noninferior specificity at 79% versus 84%. "What's especially promising in this study is that we looked at a range of different datasets that reflected the breadth of TB presentation, different equipment and different clinical workflows," said co-study author Sahar Kazemzadeh, software engineer at Google Health. The AI system achieved thresholds set by the World Health Organization in 2014 as a reasonable requirement for any TB screening test in most of the data sets, noted Bram van Ginneken, a professor of medical image analysis at Radboud University Medical Center in Nijmegen, The Netherlands, in an editorial accompanying the study. Yet, he added: "It is shown that for difficult data sets, such as a mining population, whose radiographs may contain other signs of lung disease, and a subset of subjects who are HIV positive, where TB may occur without typical radiographic abnormalities, both the AI software and the human readers performed much lower.

Most NER methods rely on extensive labeled data for model training, which struggles in the low-resource scenarios with limited training data. Existing dominant approaches usually suffer from the challenge that the target domain has different label sets compared with a resource-rich source domain, which can be concluded as class transfer and domain transfer. In this paper, we propose a lightweight tuning paradigm for low-resource NER via pluggable prompting (LightNER). Specifically, we construct the unified learnable verbalizer of entity categories to generate the entity span sequence and entity categories without any label-specific classifiers, thus addressing the class transfer issue. We further propose a pluggable guidance module by incorporating learnable parameters into the self-attention layer as guidance, which can re-modulate the attention and adapt pre-trained weights. Note that we only tune those inserted module with the whole parameter of the pre-trained language model fixed, thus, making our approach lightweight and flexible for low-resource scenarios and can better transfer knowledge across domains. Experimental results show that LightNER can obtain comparable performance in the standard supervised setting and outperform strong baselines in low-resource settings. Code is in https://github.com/zjunlp/DeepKE/tree/main/example/ner/few-shot.

People say, "A picture is worth a thousand words". Then how can we get the rich information out of the image? We argue that by using visual clues to bridge large pretrained vision foundation models and language models, we can do so without any extra cross-modal training. Thanks to the strong zero-shot capability of foundation models, we start by constructing a rich semantic representation of the image (e.g., image tags, object attributes / locations, captions) as a structured textual prompt, called visual clues, using a vision foundation model. Based on visual clues, we use large language model to produce a series of comprehensive descriptions for the visual content, which is then verified by the vision model again to select the candidate that aligns best with the image. We evaluate the quality of generated descriptions by quantitative and qualitative measurement. The results demonstrate the effectiveness of such a structured semantic representation.