We will continue these experiments and add the results into our appendix part.

We will continue these experiments and add the results into our appendix part.

The linking of clinical entities is a crucial part of extracting structured information from clinical texts. It is the process of assigning a code from a medical ontology or classification to a phrase in the text. The International Classification of Diseases - 10th revision (ICD-10) is an international standard for classifying diseases for statistical and insurance purposes. Automatically assigning the correct ICD-10 code to terms in discharge summaries will simplify the work of healthcare professionals and ensure consistent coding in hospitals. Our paper proposes an approach for linking clinical terms to ICD-10 codes in different languages using Large Language Models (LLMs). The approach consists of a multistage pipeline that uses clinical dictionaries to match unambiguous terms in the text and then applies in-context learning with GPT-4.1 to predict the ICD-10 code for the terms that do not match the dictionary. Our system shows promising results in predicting ICD-10 codes on different benchmark datasets in Spanish - 0.89 F1 for categories and 0.78 F1 on subcategories on CodiEsp, and Greek - 0.85 F1 on ElCardioCC.

Breakthroughs, discoveries, and DIY tips sent every weekday. Walk down the supplement aisle at your local drugstore and you'll likely spot bottles of NAD (nicotinamide adenine dinucleotide) pills, powders, or liquids that promise to slow down aging. The global market for these products hit 535.53 million in 2022. But do NAD supplements really work? "I get asked about NAD supplements occasionally by patients," says Dr. Nicholas Dragolea, a London-based GP with an interest in longevity and functional health at My Longevity Centre in the United Kingdom.

This research explores the applicability of cross-lingual transfer learning from English to Japanese and Indonesian using the XLM-R pre-trained model. The results are compared with several previous works, either by models using a similar zero-shot approach or a fully-supervised approach, to provide an overview of the zero-shot transfer learning approach's capability using XLM-R in comparison with existing models. Our models achieve the best result in one Japanese dataset and comparable results in other datasets in Japanese and Indonesian languages without being trained using the target language. Furthermore, the results suggest that it is possible to train a multi-lingual model, instead of one model for each language, and achieve promising results.

Self-supervised learning (SSL) has shown promising results in various speech and natural language processing applications. However, its efficacy in music information retrieval (MIR) still remains largely unexplored. While previous SSL models pre-trained on music recordings may have been mostly closed-sourced, recent speech models such as wav2vec2.0 have shown promise in music modelling. Nevertheless, research exploring the effectiveness of applying speech SSL models to music recordings has been limited. We explore the music adaption of SSL with two distinctive speech-related models, data2vec1.0 and Hubert, and refer to them as music2vec and musicHuBERT, respectively. We train $12$ SSL models with 95M parameters under various pre-training configurations and systematically evaluate the MIR task performances with 13 different MIR tasks. Our findings suggest that training with music data can generally improve performance on MIR tasks, even when models are trained using paradigms designed for speech. However, we identify the limitations of such existing speech-oriented designs, especially in modelling polyphonic information. Based on the experimental results, empirical suggestions are also given for designing future musical SSL strategies and paradigms.

Retrosynthesis, which predicts the reactants of a given target molecule, is an essential task for drug discovery. In recent years, the machine learing based retrosynthesis methods have achieved promising results. In this work, we introduce RetroKNN, a local reaction template retrieval method to further boost the performance of template-based systems with non-parametric retrieval. We first build an atom-template store and a bond-template store that contain the local templates in the training data, then retrieve from these templates with a k-nearest-neighbor (KNN) search during inference. The retrieved templates are combined with neural network predictions as the final output. Furthermore, we propose a lightweight adapter to adjust the weights when combing neural network and KNN predictions conditioned on the hidden representation and the retrieved templates. We conduct comprehensive experiments on two widely used benchmarks, the USPTO-50K and USPTO-MIT. Especially for the top-1 accuracy, we improved 7.1% on the USPTO-50K dataset and 12.0% on the USPTO-MIT dataset. These results demonstrate the effectiveness of our method.

I recently asked Bard, Google's conversational chatbot, whether artificial intelligence would replace teachers. Here's what it said, "It is unlikely that AI will completely replace teachers in the near future." During a poetry night, I remember joking with a friend that it takes a broken heart to nurture and heal another heart. I added, "Until AI experiences heartbreaks, we must trust human teachers to nurture the hearts and minds of the next generation." Yet it's hard to ignore the growing questions and concerns emerging from -- and about -- the teaching community on the impact of AI on their jobs, their classrooms and their very vocation.

As artificial intelligence continues to get more impressive, a lab out of Waterloo, Ont., is taking breast cancer research to new heights by working to help patients get proper treatment with their new technology. When patients get breast cancer, they typically undergo a type of imaging, like a magnetic resonance imaging or MRI, to look for cancerous tumors. The Waterloo lab has created "a synthetic correlate diffusion" MRI that is tailored to capture details and properties of cancer in a way that previous MRI systems couldn't. "It could be a very helpful tool to help oncologists and medical doctors to be able to identify and personalize the type of treatment that a cancer patient gets," Alexander Wong, professor and Canada Research Chair in Artificial Intelligence and Medical Imaging at the University of Waterloo, told Global News. Breast cancer is the second leading cause of death from cancer in Canadian women, according to the Canadian Cancer Society.

Since the discovery of penicillin in the late 1920s, antibiotics have "revolutionized medicine and saved millions of lives." Unfortunately, the effectiveness of antibiotics is now threatened by the increase of antibiotic-resistant bacteria globally. Antibiotic-resistant infections cause the deaths of up to 1.2 million people annually, making them one of the leading causes of death. There are several factors contributing to this crisis of resistance to antibiotics. These include overusing and misusing antibiotics in treatments.