Automatic term extraction plays an essential role in domain language understanding and several natural language processing downstream tasks. In this paper, we propose a comparative study on the predictive power of Transformers-based pretrained language models toward term extraction in a multi-language cross-domain setting. Besides evaluating the ability of monolingual models to extract single- and multi-word terms, we also experiment with ensembles of mono- and multilingual models by conducting the intersection or union on the term output sets of different language models. Our experiments have been conducted on the ACTER corpus covering four specialized domains (Corruption, Wind energy, Equitation, and Heart failure) and three languages (English, French, and Dutch), and on the RSDO5 Slovenian corpus covering four additional domains (Biomechanics, Chemistry, Veterinary, and Linguistics). The results show that the strategy of employing monolingual models outperforms the state-of-the-art approaches from the related work leveraging multilingual models, regarding all the languages except Dutch and French if the term extraction task excludes the extraction of named entity terms. Furthermore, by combining the outputs of the two best performing models, we achieve significant improvements.

Historians will argue that other matches in World Cup history were dirtier. Think'The Battle of Santiago' in 1962, in which Chile and Italy brawled throughout and which the BBC's David Coleman described as "the most stupid, appalling, disgusting and disgraceful exhibition of football in the history of the game".

Transformer networks have seen great success in natural language processing and machine vision, where task objectives such as next word prediction and image classification benefit from nuanced context sensitivity across high-dimensional inputs. However, there is an ongoing debate about how and when transformers can acquire highly structured behavior and achieve systematic generalization. Here, we explore how well a causal transformer can perform a set of algorithmic tasks, including copying, sorting, and hierarchical compositions of these operations. We demonstrate strong generalization to sequences longer than those used in training by replacing the standard positional encoding typically used in transformers with labels arbitrarily paired with items in the sequence. We search for the layer and head configuration sufficient to solve these tasks, then probe for signs of systematic processing in latent representations and attention patterns. We show that two-layer transformers learn reliable solutions to multi-level problems, develop signs of task decomposition, and encode input items in a way that encourages the exploitation of shared computation across related tasks. These results provide key insights into how attention layers support structured computation both within a task and across multiple tasks.

This article presents a survey of literature in the area of Human-Robot Interaction (HRI), specifically on systems containing more than two agents (i.e., having multiple humans and/or multiple robots). We identify three core aspects of ``Multi-agent" HRI systems that are useful for understanding how these systems differ from dyadic systems and from one another. These are the Team structure, Interaction style among agents, and the system's Computational characteristics. Under these core aspects, we present five attributes of HRI systems, namely Team size, Team composition, Interaction model, Communication modalities, and Robot control. These attributes are used to characterize and distinguish one system from another. We populate resulting categories with examples from recent literature along with a brief discussion of their applications and analyze how these attributes differ from the case of dyadic human-robot systems. We summarize key observations from the current literature, and identify challenges and promising areas for future research in this domain. In order to realize the vision of robots being part of the society and interacting seamlessly with humans, there is a need to expand research on multi-human -- multi-robot systems. Not only do these systems require coordination among several agents, they also involve multi-agent and indirect interactions which are absent from dyadic HRI systems. Adding multiple agents in HRI systems requires advanced interaction schemes, behavior understanding and control methods to allow natural interactions among humans and robots. In addition, research on human behavioral understanding in mixed human-robot teams also requires more attention. This will help formulate and implement effective robot control policies in HRI systems with large numbers of heterogeneous robots and humans; a team composition reflecting many real-world scenarios.

We introduce OPEND, a benchmark for learning how to use a hand to open cabinet doors or drawers in a photo-realistic and physics-reliable simulation environment driven by language instruction. To solve the task, we propose a multi-step planner composed of a deep neural network and rule-base controllers. The network is utilized to capture spatial relationships from images and understand semantic meaning from language instructions. Controllers efficiently execute the plan based on the spatial and semantic understanding. We evaluate our system by measuring its zero-shot performance in test data set. Experimental results demonstrate the effectiveness of decision planning by our multi-step planner for different hands, while suggesting that there is significant room for developing better models to address the challenge brought by language understanding, spatial reasoning, and long-term manipulation. We will release OPEND and host challenges to promote future research in this area.

Contrastive learning has become a new paradigm for unsupervised sentence embeddings. Previous studies focus on instance-wise contrastive learning, attempting to construct positive pairs with textual data augmentation. In this paper, we propose a novel Contrastive learning method with Prompt-derived Virtual semantic Prototypes (ConPVP). Specifically, with the help of prompts, we construct virtual semantic prototypes to each instance, and derive negative prototypes by using the negative form of the prompts. Using a prototypical contrastive loss, we enforce the anchor sentence embedding to be close to its corresponding semantic prototypes, and far apart from the negative prototypes as well as the prototypes of other sentences. Extensive experimental results on semantic textual similarity, transfer, and clustering tasks demonstrate the effectiveness of our proposed model compared to strong baselines. Code is available at https://github.com/lemon0830/promptCSE.

A medical robot can guide a flexible needle through the lungs of living pigs without requiring human surgeons to directly control the robot's actions. Over several additional tests on lungs removed from the pigs, the robot placed the needle more precisely than human doctors using a standard straight needle procedure. "There are many procedures, including biopsy or directed drug delivery or localised radiation cancer treatment, that involve using a needle to get to a specific target to perform the procedure where you're manoeuvring that needle inside …

Qatar's World Cup has seen the round-of-16 games. Now, it is time for the quarter-finals. Among the biggest shocks during the World Cup this year have been the games that former champions – Brazil, Spain, Argentina and Germany – did not win. This tournament also saw teams playing for Africa, Asia, and North America represented in the round of 16 along with traditional football powerhouses South America and Europe. But behind the great football spectacle, there has been a battle taking place at the Al Jazeera offices.

Alex Svinov is the CEO and Co-founder of Insquad, the platform to build remote development teams. He believes that the future of work is in remote teams – and this notion will radically change the world as it will bring opportunity and talent closer to each other. Alex launched Insquad after facing challenges in hiring senior tech talent for his previous startup. He tried staffing services, but they were expensive and did not give a lot of value to him as a startup. So he decided to solve this problem and help the startup community as well as offer great opportunities to the talent in underprivileged countries. Alex is a serial entrepreneur and angel investor -- 10 investments in IT companies all over the world -- Forbes council member and Alchemist mentor. In the past 10 years, he has created several successful startups in industry areas that he had no experience in before -- FinTech, outsourcing, HRTech, and food service. He is passionate about making new tech products and services and helping distributed teams achieve their goals. Alex met with Bill Clinton and Queen Elizabeth in Moscow's high school. Outside of work, he's a father of 3, plays tennis and regularly participates in amateur tournaments. Today I have with me, Alex Svinov. Now, Alex is the CEO and Co-founder of Insquad, which is a platform to build remote development teams and as the world basically circulates around technology these days, it's very very important to get a great development team and remote now as we know with the pandemic has produced change the way we work. He believes that the future work is in remote teams and this notion will radically change the world as well bring opportunity and talent closer to each other. Alex launched Insquad one year ago because he faced challenges hiring senior tech talents for his previous startup. He tried staffing services but they were expensive and did not give a lot of value to him as a startup.

Assessing the quality of movements for post-stroke patients during the rehabilitation phase is vital given that there is no standard stroke rehabilitation plan for all the patients. In fact, it depends basically on the patient's functional independence and its progress along the rehabilitation sessions. To tackle this challenge and make neurorehabilitation more agile, we propose an automatic assessment pipeline that starts by recognising patients' movements by means of a shallow deep learning architecture, then measuring the movement quality using jerk measure and related measures. A particularity of this work is that the dataset used is clinically relevant, since it represents movements inspired from Fugl-Meyer a well common upper-limb clinical stroke assessment scale for stroke patients. We show that it is possible to detect the contrast between healthy and patients movements in terms of smoothness, besides achieving conclusions about the patients' progress during the rehabilitation sessions that correspond to the clinicians' findings about each case.