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.

WASHINGTON, Sept. 12, 2022 (GLOBE NEWSWIRE) -- The growing demand for AI-powered services in the form of Application Programming Interface (API) and Software Development Kit (SDK) and the growing number of innovative start-ups are some of the factors anticipated to drive the market. The Global Market revenue was valued at USD 5.9 Billion in 2021. The Global Artificial Intelligence as a Service Market size is forecast to reach USD 52.8 Billion by 2028 and is expected to grow to exhibit a Compound Annual Growth Rate (CAGR) of 44.1% during the forecast period; states Vantage Market Research, in a report, titled "Artificial Intelligence as a Service Market Size, Share & Trends Analysis Report by Technology (Deep Learning, Machine Learning, Natural Language Processing), by Verticals (Government, Banking Financial Services & Insurance (BFSI), Healthcare, Manufacturing, Retail, Telecommunication), by Region (North America, Europe, Asia Pacific, Latin America, Middle East & Africa) - Global Industry Assessment (2016 - 2021) & Forecast (2022 - 2028)". The banking, financial services, and insurance sectors experience significant expansion during the forecast period. A significant amount of client data or transaction records are produced due to the growing digital revolution in banking and the increased use of the mobile payment, e-banking, real-time money transfers, and mobile banking applications.

The graph represents a network of 2,070 Twitter users whose tweets in the requested range contained "iot ai", or who were replied to or mentioned in those tweets. The network was obtained from the NodeXL Graph Server on Wednesday, 17 August 2022 at 11:27 UTC. The requested start date was Wednesday, 17 August 2022 at 00:01 UTC and the maximum number of tweets (going backward in time) was 7,500. The tweets in the network were tweeted over the 1-day, 18-hour, 9-minute period from Monday, 15 August 2022 at 05:51 UTC to Wednesday, 17 August 2022 at 00:00 UTC. Additional tweets that were mentioned in this data set were also collected from prior time periods.

Convergint, a global leader in service-based systems integration, announced it has acquired MVP Tech, a leading UAE-based security and IT systems contractor serving private enterprises and government clients for the past two decades. The acquisition will add more than 200 colleagues to Convergint and expand the company's presence to countries in the Gulf Cooperation Council (GCC) and Middle East. "By joining forces with Convergint, we now have the opportunity to expand our engineering-driven philosophy and to further elevate our service capabilities, for both our local and multinational customers" Founded in 2003 and headquartered in Dubai, MVP Tech has three offices across the United Arab Emirates and Iraq with near-future expansion plans into KSA. The company's diverse and multinational colleagues are comprised of 80% technical individuals with a proven industry background, managing and delivering projects with one of the largest on-the-ground workforces in the market. MVP Tech's mission is to deliver next-generation intelligence and interconnectivity across verticals such as critical infrastructure, hospitality, luxury retail and malls, and energy infrastructure.

Language identification is critical for many downstream tasks in automatic speech recognition (ASR), and is beneficial to integrate into multilingual end-to-end ASR as an additional task. In this paper, we propose to modify the structure of the cascaded-encoder-based recurrent neural network transducer (RNN-T) model by integrating a per-frame language identifier (LID) predictor. RNN-T with cascaded encoders can achieve streaming ASR with low latency using first-pass decoding with no right-context, and achieve lower word error rates (WERs) using second-pass decoding with longer right-context. By leveraging such differences in the right-contexts and a streaming implementation of statistics pooling, the proposed method can achieve accurate streaming LID prediction with little extra test-time cost. Experimental results on a voice search dataset with 9 language locales shows that the proposed method achieves an average of 96.2% LID prediction accuracy and the same second-pass WER as that obtained by including oracle LID in the input.