Translating natural language questions into SPARQL queries enables Knowledge Base querying for factual and up-to-date responses. However, existing datasets for this task are predominantly template-based, leading models to learn superficial mappings between question and query templates rather than developing true generalization capabilities. As a result, models struggle when encountering naturally phrased, template-free questions. This paper introduces FRASE (FRAme-based Semantic Enhancement), a novel approach that leverages Frame Semantic Role Labeling (FSRL) to address this limitation. We also present LC-QuAD 3.0, a new dataset derived from LC-QuAD 2.0, in which each question is enriched using FRASE through frame detection and the mapping of frame-elements to their argument. We evaluate the impact of this approach through extensive experiments on recent large language models (LLMs) under different fine-tuning configurations. Our results demonstrate that integrating frame-based structured representations consistently improves SPARQL generation performance, particularly in challenging generalization scenarios when test questions feature unseen templates (unknown template splits) and when they are all naturally phrased (reformulated questions).

Linguistic ambiguity continues to represent a significant challenge for natural language processing (NLP) systems, notwithstanding the advancements in architectures such as Transformers and BERT. Inspired by the recent success of instructional models like ChatGPT and Gemini (In 2023, the artificial intelligence was called Bard.), this study aims to analyze and discuss linguistic ambiguity within these models, focusing on three types prevalent in Brazilian Portuguese: semantic, syntactic, and lexical ambiguity. We create a corpus comprising 120 sentences, both ambiguous and unambiguous, for classification, explanation, and disambiguation. The models capability to generate ambiguous sentences was also explored by soliciting sets of sentences for each type of ambiguity. The results underwent qualitative analysis, drawing on recognized linguistic references, and quantitative assessment based on the accuracy of the responses obtained. It was evidenced that even the most sophisticated models, such as ChatGPT and Gemini, exhibit errors and deficiencies in their responses, with explanations often providing inconsistent. Furthermore, the accuracy peaked at 49.58 percent, indicating the need for descriptive studies for supervised learning.

The goal of this study is to investigate whether a Transformer-based neural language model infers lexical semantics and use this information for the completion of morphosyntactic patterns. The semantic properties considered are telicity (also combined with definiteness) and agentivity. Both act at the interface between semantics and morphosyntax: they are semantically determined and syntactically encoded. The tasks were submitted to both the computational model and a group of Italian native speakers. The comparison between the two groups of data allows us to investigate to what extent neural language models capture significant aspects of human semantic competence.

Virtually every industry stays updated on the year's latest technology trends. New technologies are rapidly advancing, and businesses across every sector want to invest in them to reap the benefits -- companies in the marketing industry are no exception. The digital marketing landscape is ever-changing, and a primary factor affecting marketers is new tech innovations. Many principles remain the same over time, but professionals can continue following them and integrate new technologies simultaneously. The metaverse is a network of unique, immersive, and virtual spaces where users have personal avatars.

DISCLOSURE: THIS MESSAGE MAY CONTAIN AN AFFILIATE LINK, MEANING I GET A SMALL COMMISSION IF YOU DECIDE TO MAKE A PURCHASE USING MY LINK AT NO ADDITIONAL COST TO YOU. Frase offers top-ranking keywords and headlines for your topic. With Frase, you have access to frequently asked questions regarding your content and the external links connected to your subject. With Frase, content creation has never been easier! When I contemplated starting a blog, consistent content creation was at the top of my concerns list. Where will I find reliable sources? How can I ensure I am providing the most value for my work?

As an entrepreneur, time is your most valuable resource. So, to get the most out of it, you better challenge yourself to see how and where technology can help you gain more time. However, as an advocate of disruptive technologies, I am constantly exploring how new solutions and artificial intelligence can not only streamline my business but also be far more impactful. And I can tell you, it's fascinating to see the effect. So, here are the eight AI-powered products that help me reach my business goals.

The idea that computers will soon steal our jobs is an article of faith among many of the world's most powerful people. The argument goes like this: breakthroughs in robotics and artificial intelligence will make it possible to automate various kinds of labour. Self-driving cars will replace taxi and truck drivers; software will replace lawyers and accountants. We'll end up with a world where machines do almost all of the work. Over the last few years, a growing chorus of pundits, academics and executives have made this scenario seem inevitable – and imminent. There are many reasons to be sceptical of their claims.

The most vexing and important issues of the present and the future likely will be solved using the power of supercomputers, a renowned expert says. In fact, supercomputers already are being used to tackle problems in disciplines such as medicine, education, energy exploration and criminal investigation, explained Katharine Frase. That kind of readily available technology, she said, is leading to increased capabilities in policing and other disciplines "in an actionable way." Frase was the keynote speaker Tuesday at SC16, the top international convention showcasing how high-performance computing, networking, storage and analysis are advancing commerce, education, medicine, scientific research, space exploration, weather forecasting and many other disciplines. Frase served as chief technology officer and vice president of public sector at IBM from March 2013 to September 2015.