Here, we characterize the radiology report as a distinct domain and introduce RaLEs, the Radiology Language Evaluations, as a benchmark for natural language understanding and generation in radiology.

The radiology report is the main form of communication between radiologists and other clinicians. Prior work in natural language processing in radiology reports has shown the value of developing methods tailored for individual tasks such as identifying reports with critical results or disease detection. Meanwhile, English and biomedical natural language understanding benchmarks such as the General Language Understanding and Evaluation as well as Biomedical Language Understanding and Reasoning Benchmark have motivated the development of models that can be easily adapted to address many tasks in those domains. Here, we characterize the radiology report as a distinct domain and introduce RaLEs, the Radiology Language Evaluations, as a benchmark for natural language understanding and generation in radiology. RaLEs is comprised of seven natural language understanding and generation evaluations including the extraction of anatomical and disease entities and their relations, procedure selection, and report summarization. We characterize the performance of models designed for the general, biomedical, clinical and radiology domains across these tasks. We find that advances in the general and biomedical domains do not necessarily translate to radiology, and that improved models from the general domain can perform comparably to smaller clinical-specific models. The limited performance of existing pre-trained models on RaLEs highlights the opportunity to improve domain-specific self-supervised models for natural language processing in radiology. We propose RaLEs as a benchmark to promote and track the development of such domain-specific radiology language models.

Here, we characterize the radiology report as a distinct domain and introduce RaLEs, the Radiology Language Evaluations, as a benchmark for natural language understanding and generation in radiology.

The radiology report is the main form of communication between radiologists and other clinicians. Prior work in natural language processing in radiology reports has shown the value of developing methods tailored for individual tasks such as identifying reports with critical results or disease detection. Meanwhile, English and biomedical natural language understanding benchmarks such as the General Language Understanding and Evaluation as well as Biomedical Language Understanding and Reasoning Benchmark have motivated the development of models that can be easily adapted to address many tasks in those domains. Here, we characterize the radiology report as a distinct domain and introduce RaLEs, the Radiology Language Evaluations, as a benchmark for natural language understanding and generation in radiology. RaLEs is comprised of seven natural language understanding and generation evaluations including the extraction of anatomical and disease entities and their relations, procedure selection, and report summarization.

This work proposes a new kinematics of a myoelectric hand prosthesis with a single actuator, allowing to realize the tridigital grip but also the lateral grip. Inspired by tridigital prostheses, which are simpler, more robust and less expensive than polydigital prostheses, this new kinematics aims at proposing an accessible prosthesis (affordable, easy-to-use, robust, easy-to-repair). Cables are used instead of a rigid rod to transmit the movement bewteen the upper fingers and the thumb. The methods and design choices are detailed in this article. To conclude, the evaluation of the prototype by an experimented user leads to a first discussion of the results.

The inside of a tokamak--the doughnut-shaped vessel designed to contain a nuclear fusion reaction--presents a special kind of chaos. Hydrogen atoms are smashed together at unfathomably high temperatures, creating a whirling, roiling plasma that's hotter than the surface of the sun. Finding smart ways to control and confine that plasma will be key to unlocking the potential of nuclear fusion, which has been mooted as the clean energy source of the future for decades. At this point, the science underlying fusion seems sound, so what remains is an engineering challenge. "We need to be able to heat this matter up and hold it together for long enough for us to take energy out of it," says Ambrogio Fasoli, director of the Swiss Plasma Center at École Polytechnique Fédérale de Lausanne in Switzerland.

Tiny mobile robots are learning to work with insects in the hope the creatures' sensitive antennae and ability to squeeze into small spaces can be put to use serving humans. With a soft electronic whirr, a rather unusual looking ant trundles along behind a column of its arthropod comrades as they march off to fetch some food. While the little insects begin ferrying tiny globules of sugar back home, their mechanical companion bustles forward to effortlessly pick up the entire container and carry it back to the nest. It is a dramatic demonstration of how robots can be introduced and accepted into insect societies. But the research, which is being conducted as part of the EU-funded CyBioSys project, could be an important step towards using robots to subtly control, or work alongside, animals or humans.

Cyberbotics Ltd. is launching https://robotbenchmark.net to allow everyone to program simulated robots online for free. Robotbenchmark offers a series of robot programming challenges that address various topics across a wide range of difficulty levels, from middle school to PhD. Users don't need to install any software on their computer, cloud-based 3D robotics simulations run on a web page. They can learn programming by writing Python code to control robot behavior. The performance achieved by users is recorded and displayed online, so that they can challenge their friends and show off their skills at robot programming on social networks.