Laser processing is a rapidly growing key technology driven by several advantages such as cost and performance. Laser welding presents numerous advantages in comparison with other welding technologies, providing high reliability and cost-effective solutions. Significant interest in this technology, combined with the increasing demand for high-strength lightweight structures has led to an increasing interest in joining high-performance engineering thermoplastics by employing laser technologies. Laser transmission welding is the base method usually employed to successfully join two polymers, a transmitting one through which the laser penetrates, and another one responsible for absorbing the laser radiation, resulting in heat and melting of the two components. In this work, the weldability of solely transmitting high-performance engineering thermoplastic is analyzed. ERTALON ® 6 SA, in its white version, is welded by a pulsed Nd:YAG laser. Tensile tests were performed in order to evaluate the quality of each joint by assessing its strength. A numerical model of the joint is also developed to support the theoretical approaches employed to justify the experimental observations.

Resumo: Com o crescente aumento do volume de informações disponíveis na web, as ferramentas de busca tornam-se cada vez mais necessárias no dia a dia dos usuários da internet. Entretanto, pessoas mal-intencionadas veem esse fenômeno como uma oportunidade para obter lucro e, como consequência, um problema conhecido como web spam vem se tornando cada vez mais frequente na vida dos usuários da internet, provocando prejuízos pessoais e econômicos. Diversas técnicas vêm sendo propostas para detecção automática de web spam, porém, a alta capacidade de aperfeiço-amento dos mecanismos empregados pelos spammers exige que os métodos de classificação sejam cada vez mais genéricos e eficientes. Técnicas bastante conhecidas que possuem tais características são as redes neurais artificiais. Diante desse cenário desafiador, estse trabalho apresenta uma aná-lise de desempenho de redes neurais artificiais perceptron de múltiplas camadas no combate de tal problema. Palavras IntroduçãoJunto com o constante aumento do número de usuários, a web também vem crescendo de maneira impressionante e está se tornando cada vez mais importante na vida das pessoas que a utilizam. Tal crescimento, aliado ao consequente aumento no volume de informações disponíveis, faz aumentar a importância dos motores de busca, que são ferramentas que ajudam os usuários a encontrar as informações desejadas, visando apresentar os resultados de forma organizada, rápida e eficiente. Porém, existem métodos mal-intencionados que tentam burlar os mecanismos de busca manipulando o ranking de relevância das páginas apresentadas, degradando a eficiência dessas ferramentas. Esses métodos induzem os algoritmos de busca a classificar algumas páginas com maior relevância do que realmente têm, o que deteriora os resultados e frustra os usuários, além de os expor a conteúdo inadequado e inseguro. Essa técnica enganosa é conhecida como web spamming [35].

The Covid-19 pandemic urged the scientific community to join efforts at an unprecedented scale, leading to faster than ever dissemination of data and results, which in turn motivated more research works. This paper presents and discusses information retrieval models aimed at addressing the challenge of searching the large number of publications that stem from these studies.The model presented, based on classical baselines followed by an interaction based neural ranking model, was evaluated and evolved within the TREC Covid challenge setting. Results on this dataset show that, when starting with a strong baseline, our light neural ranking model can achieve results that are comparable to other model architectures that use very large number of parameters.

Question answering can be described as retrieving relevant information for questions expressed in natural language, possibly also generating a natural language answer. This paper presents a pipeline for document and passage retrieval for biomedical question answering built around a new variant of the DeepRank network model in which the recursive layer is replaced by a self-attention layer combined with a weighting mechanism. This adaptation halves the total number of parameters and makes the network more suited for identifying the relevant passages in each document. The overall retrieval system was evaluated on the BioASQ tasks 6 and 7, achieving similar retrieval performance when compared to more complex network architectures.

The identification of chemicals in articles has attracted a large interest in the biomedical scientific community, given its importance in drug development research. Most of previous research have focused on PubMed abstracts, and further investigation using full-text documents is required because these contain additional valuable information that must be explored. The manual expert task of indexing Medical Subject Headings (MeSH) terms to these articles later helps researchers find the most relevant publications for their ongoing work. The BioCreative VII NLM-Chem track fostered the development of systems for chemical identification and indexing in PubMed full-text articles. Chemical identification consisted in identifying the chemical mentions and linking these to unique MeSH identifiers. This manuscript describes our participation system and the post-challenge improvements we made. We propose a three-stage pipeline that individually performs chemical mention detection, entity normalization and indexing. Regarding chemical identification, we adopted a deep-learning solution that utilizes the PubMedBERT contextualized embeddings followed by a multilayer perceptron and a conditional random field tagging layer. For the normalization approach, we use a sieve-based dictionary filtering followed by a deep-learning similarity search strategy. Finally, for the indexing we developed rules for identifying the more relevant MeSH codes for each article. During the challenge, our system obtained the best official results in the normalization and indexing tasks despite the lower performance in the chemical mention recognition task. In a post-contest phase we boosted our results by improving our named entity recognition model with additional techniques. The final system achieved 0.8731, 0.8275 and 0.4849 in the chemical identification, normalization and indexing tasks, respectively. The code to reproduce our experiments and run the pipeline is publicly available. Database URL https://github.com/bioinformatics-ua/biocreativeVII_track2