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.

Knowledge graph (KG) embedding seeks to learn vector representations for entities and relations. Conventional models reason over graph structures, but they suffer from the issues of graph incompleteness and long-tail entities. Recent studies have used pre-trained language models to learn embeddings based on the textual information of entities and relations, but they cannot take advantage of graph structures. In the paper, we show empirically that these two kinds of features are complementary for KG embedding. To this end, we propose CoLE, a Co-distillation Learning method for KG Embedding that exploits the complementarity of graph structures and text information. Its graph embedding model employs Transformer to reconstruct the representation of an entity from its neighborhood subgraph. Its text embedding model uses a pre-trained language model to generate entity representations from the soft prompts of their names, descriptions, and relational neighbors. To let the two model promote each other, we propose co-distillation learning that allows them to distill selective knowledge from each other's prediction logits. In our co-distillation learning, each model serves as both a teacher and a student. Experiments on benchmark datasets demonstrate that the two models outperform their related baselines, and the ensemble method CoLE with co-distillation learning advances the state-of-the-art of KG embedding.

Recent years have witnessed great progress on applying pre-trained language models, e.g., BERT, to information retrieval (IR) tasks. Hyperlinks, which are commonly used in Web pages, have been leveraged for designing pre-training objectives. For example, anchor texts of the hyperlinks have been used for simulating queries, thus constructing tremendous query-document pairs for pre-training. However, as a bridge across two web pages, the potential of hyperlinks has not been fully explored. In this work, we focus on modeling the relationship between two documents that are connected by hyperlinks and designing a new pre-training objective for ad-hoc retrieval. Specifically, we categorize the relationships between documents into four groups: no link, unidirectional link, symmetric link, and the most relevant symmetric link. By comparing two documents sampled from adjacent groups, the model can gradually improve its capability of capturing matching signals. We propose a progressive hyperlink predication ({PHP}) framework to explore the utilization of hyperlinks in pre-training. Experimental results on two large-scale ad-hoc retrieval datasets and six question-answering datasets demonstrate its superiority over existing pre-training methods.

Decrypting intelligence from the human brain construct is vital in the detection of particular neurological disorders. Recently, functional brain connectomes have been used successfully to predict behavioral scores. However, state-of-the-art methods, on one hand, neglect the topological properties of the connectomes and, on the other hand, fail to solve the high inter-subject brain heterogeneity. To address these limitations, we propose a novel regression graph neural network through meta-learning namely Meta-RegGNN for predicting behavioral scores from brain connectomes. The parameters of our proposed regression GNN are explicitly trained so that a small number of gradient steps combined with a small training data amount produces a good generalization to unseen brain connectomes. Our results on verbal and full-scale intelligence quotient (IQ) prediction outperform existing methods in both neurotypical and autism spectrum disorder cohorts. Furthermore, we show that our proposed approach ensures generalizability, particularly for autistic subjects. Our Meta-RegGNN source code is available at https://github.com/basiralab/Meta-RegGNN.

Treebank selection for parsing evaluation and the spurious effects that might arise from a biased choice have not been explored in detail. This paper studies how evaluating on a single subset of treebanks can lead to weak conclusions. First, we take a few contrasting parsers, and run them on subsets of treebanks proposed in previous work, whose use was justified (or not) on criteria such as typology or data scarcity. Second, we run a large-scale version of this experiment, create vast amounts of random subsets of treebanks, and compare on them many parsers whose scores are available. The results show substantial variability across subsets and that although establishing guidelines for good treebank selection is hard, it is possible to detect potentially harmful strategies.

Over the years, reasoning over knowledge graphs (KGs), which aims to infer new conclusions from known facts, has mostly focused on static KGs. The unceasing growth of knowledge in real life raises the necessity to enable the inductive reasoning ability on expanding KGs. Existing inductive work assumes that new entities all emerge once in a batch, which oversimplifies the real scenario that new entities continually appear. This study dives into a more realistic and challenging setting where new entities emerge in multiple batches. We propose a walk-based inductive reasoning model to tackle the new setting. Specifically, a graph convolutional network with adaptive relation aggregation is designed to encode and update entities using their neighboring relations. To capture the varying neighbor importance, we employ a query-aware feedback attention mechanism during the aggregation. Furthermore, to alleviate the sparse link problem of new entities, we propose a link augmentation strategy to add trustworthy facts into KGs. We construct three new datasets for simulating this multi-batch emergence scenario. The experimental results show that our proposed model outperforms state-of-the-art embedding-based, walk-based and rule-based models on inductive KG reasoning.

Bill Gates has called for greater investment in engineered crops that can adapt to climate change and resist agricultural pests, in an effort to solve world hunger. In the latest annual Goalkeepers Report from the Bill & Melinda Gates Foundation, Gates says the global hunger crisis is so immense that food aid cannot fully address the problem. What's also needed, he argues, are innovations in farming technology that can help to reverse the crisis. Gates points in particular to a breakthrough he calls'magic seeds' - including maize that has been bred to be more resistant to hotter, drier climates, and rice that requires three fewer weeks in the field. These innovations will allow agricultural productivity to increase despite the changing climate, he argues.