Zobrazeno 1 - 10
of 348
pro vyhledávání: '"Simperl, Elena"'
Knowing more about the data used to build AI systems is critical for allowing different stakeholders to play their part in ensuring responsible and appropriate deployment and use. Meanwhile, a 2023 report shows that data transparency lags significant
Externí odkaz:
http://arxiv.org/abs/2409.03307
Autor:
Zhao, Yihang, Zhang, Bohui, Hu, Xi, Ouyang, Shuyin, Kim, Jongmo, Jain, Nitisha, de Berardinis, Jacopo, Meroño-Peñuela, Albert, Simperl, Elena
Past ontology requirements engineering (ORE) has primarily relied on manual methods, such as interviews and collaborative forums, to gather user requirements from domain experts, especially in large projects. Current OntoChat offers a framework for O
Externí odkaz:
http://arxiv.org/abs/2408.15256
Autor:
Koutsiana, Elisavet, Walker, Johanna, Nwachukwu, Michelle, Meroño-Peñuela, Albert, Simperl, Elena
Despite many advances in knowledge engineering (KE), challenges remain in areas such as engineering knowledge graphs (KGs) at scale, keeping up with evolving domain knowledge, multilingualism, and multimodality. Recently, KE has used LLMs to support
Externí odkaz:
http://arxiv.org/abs/2408.08878
Autor:
Koutsiana, Elisavet, Reklos, Ioannis, Alghamdi, Kholoud Saad, Jain, Nitisha, Meroño-Peñuela, Albert, Simperl, Elena
We study collaboration patterns of Wikidata, one of the world's largest collaborative knowledge graph communities. Wikidata lacks long-term engagement with a small group of priceless members, 0.8%, to be responsible for 80% of contributions. Therefor
Externí odkaz:
http://arxiv.org/abs/2407.18278
Autor:
Jain, Nitisha, Akhtar, Mubashara, Giner-Miguelez, Joan, Shinde, Rajat, Vanschoren, Joaquin, Vogler, Steffen, Goswami, Sujata, Rao, Yuhan, Santos, Tim, Oala, Luis, Karamousadakis, Michalis, Maskey, Manil, Marcenac, Pierre, Conforti, Costanza, Kuchnik, Michael, Aroyo, Lora, Benjelloun, Omar, Simperl, Elena
Data is critical to advancing AI technologies, yet its quality and documentation remain significant challenges, leading to adverse downstream effects (e.g., potential biases) in AI applications. This paper addresses these issues by introducing Croiss
Externí odkaz:
http://arxiv.org/abs/2407.16883
Wikipedia is one of the most popular websites in the world, serving as a major source of information and learning resource for millions of users worldwide. While motivations for its usage vary, prior research suggests shallow information gathering --
Externí odkaz:
http://arxiv.org/abs/2405.10205
Autor:
Akhtar, Mubashara, Benjelloun, Omar, Conforti, Costanza, Gijsbers, Pieter, Giner-Miguelez, Joan, Jain, Nitisha, Kuchnik, Michael, Lhoest, Quentin, Marcenac, Pierre, Maskey, Manil, Mattson, Peter, Oala, Luis, Ruyssen, Pierre, Shinde, Rajat, Simperl, Elena, Thomas, Goeffry, Tykhonov, Slava, Vanschoren, Joaquin, van der Velde, Jos, Vogler, Steffen, Wu, Carole-Jean
Data is a critical resource for Machine Learning (ML), yet working with data remains a key friction point. This paper introduces Croissant, a metadata format for datasets that simplifies how data is used by ML tools and frameworks. Croissant makes da
Externí odkaz:
http://arxiv.org/abs/2403.19546
This research investigates User Experience (UX) issues in dataset search, targeting Google Dataset Search and data.europa.eu. It focuses on 6 areas within UX: Initial Interaction, Search Process, Dataset Exploration, Filtering and Sorting, Dataset Ac
Externí odkaz:
http://arxiv.org/abs/2403.15861
Generating natural language text from graph-structured data is essential for conversational information seeking. Semantic triples derived from knowledge graphs can serve as a valuable source for grounding responses from conversational agents by provi
Externí odkaz:
http://arxiv.org/abs/2402.01495
Conversational question answering systems often rely on semantic parsing to enable interactive information retrieval, which involves the generation of structured database queries from a natural language input. For information-seeking conversations ab
Externí odkaz:
http://arxiv.org/abs/2401.01711