Rosario Uceda-Sosa
Research Subjects
Rosario Uceda-Sosa has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Achille Fokoue
IBM Research
2 shared publications - Elton Soares
IBM Research
2 shared publications - Guilherme Lima
IBM Research Brazil
2 shared publications - Maria Chang
IBM Research
2 shared publications - Alexander Gray1 shared publication
- Alexandre Rademaker
IBM Research Brazil
1 shared publication
Latest Publications
- Open Access
Domain specific ontologies from Linked Open Data (LOD)
Logical and probabilistic reasoning tasks that require a deeper knowledge of semantics are increasingly relying on general purpose ontologies such as Wikidata and DBpedia. However, tasks such as entity disambiguation and linking may benefit from domain specific knowledge graphs, which make it more efficient to consume the knowledge and easier to extend with proprietary content. We discuss our experience bootstrapping one such ontology for IT with a domain-agnostic pipeline, and extending it using domain-specific glossaries.
Open AccessDomain specific ontologies from Linked Open Data (LOD)
Logical and probabilistic reasoning tasks that require a deeper knowledge of semantics are increasingly relying on general purpose ontologies such as Wikidata and DBpedia. However, tasks such as entity disambiguation and linking may benefit from domain specific knowledge graphs, which make it more efficient to consume the knowledge and easier to extend with proprietary content. We discuss our experience bootstrapping one such ontology for IT with a domain-agnostic pipeline, and extending it using domain-specific glossaries.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 531-540
Conceptual Diagnostics for Knowledge Graphs and Large Language Models
Rosario Uceda Sosa, Maria Chang, Karthikeyan Natesan Ramamurthy, Moninder Singh. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 531-540
Open AccessConceptual Diagnostics for Knowledge Graphs and Large Language Models
Rosario Uceda Sosa, Maria Chang, Karthikeyan Natesan Ramamurthy, Moninder Singh. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track). 2025.
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (21) , 22871-22877
CHRONOS: A Schema-Based Event Understanding and Prediction System
Chronological and Hierarchical Reasoning Over Naturally Occurring Schemas (CHRONOS) is a system that combines language model-based natural language processing with symbolic knowledge representations to analyze and make predictions about newsworthy events. CHRONOS consists of an event-centric information extraction pipeline and a complex event schema instantiation and prediction system. Resulting predictions are detailed with arguments, event types from Wikidata, schema-based justifications, and source document provenance. We evaluate our system by its ability to capture the structure of unseen events described in news articles and make plausible predictions as judged by human annotators.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (21) , 22871-22877
Open AccessCHRONOS: A Schema-Based Event Understanding and Prediction System
Chronological and Hierarchical Reasoning Over Naturally Occurring Schemas (CHRONOS) is a system that combines language model-based natural language processing with symbolic knowledge representations to analyze and make predictions about newsworthy events. CHRONOS consists of an event-centric information extraction pipeline and a complex event schema instantiation and prediction system. Resulting predictions are detailed with arguments, event types from Wikidata, schema-based justifications, and source document provenance. We evaluate our system by its ability to capture the structure of unseen events described in news articles and make plausible predictions as judged by human annotators.
- 2 December 2023
- Published by Springer Nature
- p. 55-71
ULKB Logic: A HOL-Based Framework for Reasoning over Knowledge Graphs
- 2 December 2023
- Published by Springer Nature
- p. 55-71
ULKB Logic: A HOL-Based Framework for Reasoning over Knowledge Graphs
- Open Access
Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning
Text-based reinforcement learning agents have predominantly been neural network-based models with embeddings-based representation, learning uninterpretable policies that often do not generalize well to unseen games. On the other hand, neuro-symbolic methods, specifically those that leverage an intermediate formal representation, are gaining significant attention in language understanding tasks. This is because of their advantages ranging from inherent interpretability, the lesser requirement of training data, and being generalizable in scenarios with unseen data. Therefore, in this paper, we propose a modular, NEuro-Symbolic Textual Agent (NESTA) that combines a generic semantic parser with a rule induction system to learn abstract interpretable rules as policies. Our experiments on established text-based game benchmarks show that the proposed NESTA method outperforms deep reinforcement learning-based techniques by achieving better generalization to unseen test games and learning from fewer training interactions.
Open AccessLearning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning
Text-based reinforcement learning agents have predominantly been neural network-based models with embeddings-based representation, learning uninterpretable policies that often do not generalize well to unseen games. On the other hand, neuro-symbolic methods, specifically those that leverage an intermediate formal representation, are gaining significant attention in language understanding tasks. This is because of their advantages ranging from inherent interpretability, the lesser requirement of training data, and being generalizable in scenarios with unseen data. Therefore, in this paper, we propose a modular, NEuro-Symbolic Textual Agent (NESTA) that combines a generic semantic parser with a rule induction system to learn abstract interpretable rules as policies. Our experiments on established text-based game benchmarks show that the proposed NESTA method outperforms deep reinforcement learning-based techniques by achieving better generalization to unseen test games and learning from fewer training interactions.
- 22 May 2023
- Published by Springer Nature
- p. 661-678
Enabling Live SPARQL Queries over ConceptNet Using Triple Pattern Fragments
- 22 May 2023
- Published by Springer Nature
- p. 661-678
Enabling Live SPARQL Queries over ConceptNet Using Triple Pattern Fragments