Publications

• SylloBio-NLI: Evaluating Large Language Models on Biomedical Syllogistic Reasoning

  • Authors: Magdalena Wysocka, Danilo Carvalho, Oskar Wysocki, Marco Valentino, Andre Freitas
  • In: Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
  • Year: 2025
  • Subject: Biomedical Reasoning, Large Language Models, Explainable and safe AI

• LangVAE and LangSpace: Building and Probing for Language Model VAEs

  • Authors: Danilo S. Carvalho, Yingji Zhang, Harriet Unsworth, André Freitas
  • In: (preprint)
  • Year: 2025
  • Subject: Language Model VAEs, Representation Learning, Explainable and safe AI, Natural Language Processing
  • DOI: 10.48550/arXiv.2505.00004

• Inductive Learning of Logical Theories with LLMs: An Expressivity-Graded Analysis

  • Authors: João Pedro Gandarela, Danilo S. Carvalho, André Freitas
  • In: Proceedings of The 39th Annual AAAI Conference on Artificial Intelligence: AAAI 2025
  • Year: 2025
  • Subject: Inductive Logic Programming, Large Language Models, Explainable and safe AI
  • DOI: 10.1609/aaai.v39i22.34546

• Montague semantics and modifier consistency measurement in neural language models

  • Authors: Danilo S. Carvalho, Edoardo Manino, Julia Rozanova, Lucas Cordeiro, André Freitas
  • In: Proceedings of The 31st International Conference on Computational Linguistics: COLING 2025
  • Year: 2025
  • Subject: Representation Learning, Metamorphic Testing, Large Language Models, Explainable and safe AI, Natural Language Processing

• Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networks

  • Authors: Yingji Zhang, Danilo Carvalho, Andre Freitas
  • In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics: ACL 2024
  • Year: 2024
  • Subject: Representation Learning, Invertible Neural Networks, Explainable and safe AI, Natural Language Processing
  • DOI: 10.18653/v1/2024.acl-long.116

• An LLM-based Knowledge Synthesis and Scientific Reasoning Framework for Biomedical Discovery

  • Authors: Oskar Wysocki, Magdalena Wysocka, Danilo Carvalho, Alex Bogatu, Danilo Miranda, Maxime Delmas, Harriet Unsworth, Andre Freitas
  • In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics: ACL 2024 (Volume 3: System Demonstrations)
  • Year: 2024
  • Subject: Natural Language Inference, Biomedical Discovery
  • DOI: 10.18653/v1/2024.acl-demos.34

• Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoders

  • Authors: Yingji Zhang, Marco Valentino, Danilo Carvalho, Ian Pratt-Hartmann, Andre Freitas
  • In: Findings of the Association for Computational Linguistics: NAACL 2024
  • Year: 2024
  • Subject: Representation Learning, Variational AutoEncoders, Explainable and safe AI, Natural Language Processing
  • DOI: 10.18653/v1/2024.findings-naacl.32

• Formal Semantic Controls over Language Models

  • Authors: Danilo Carvalho, Yingji Zhang, Andre Freitas
  • In: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024): Tutorial Summaries
  • Year: 2024
  • Subject: Representation Learning, Text Embeddings, Language Model Probing, Explainable and safe AI, Natural Language Processing

• Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders

  • Authors: Yingji Zhang, Danilo Carvalho, Marco Valentino, Ian Pratt-Hartmann, Andre Freitas
  • In: Findings of the Association for Computational Linguistics: EACL 2024
  • Year: 2024
  • Subject: Representation Learning, Deep Neural models, Explainable and safe AI, Natural Language Processing

• Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions

  • Authors: Marco Valentino, Danilo Carvalho, André Freitas
  • In: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: EACL 2024
  • Year: 2024
  • Subject: Representation Learning, Deep Neural models, Explainable AI, Natural Language Processing

• Inteligência artificial interpretável: desafios e expectativas [in Portuguese]

  • Authors: Danilo S. Carvalho
  • In: Coluna Conexão Ciência e Saúde - Revista Ciência Hoje
  • Year: 2023
  • Subject: Explainable and safe AI, Popular science

• Towards Controllable Natural Language Inference through Lexical Inference Types

  • Authors: Yingji Zhang, Danilo S. Carvalho, Ian Pratt-Hartmann, Andre Freitas
  • In: (preprint)
  • Year: 2023
  • Subject: Abstract Meaning Representation, Natural Language Inference, Explainable and safe AI
  • DOI: 10.48550/arXiv.2308.03581

• Leadership and international collaboration on COVID-19 research: reducing the North-South divide?

  • Authors: Danilo S. Carvalho, Lucas L. Felipe, Priscila C. Albuquerque, Fabio Zicker, Bruna P. Fonseca
  • In: Scientometrics
  • Year: 2023
  • Subject: COVID-19, Research Leadership, Bibliometrics
  • DOI: 10.1007/s11192-023-04754-x

• Learning Disentangled Representations for Natural Language Definitions

  • Authors: Danilo S. Carvalho, Giangiacomo Mercatali, Yingji Zhang, Andre Freitas
  • In: Findings of the European chapter of Association for Computational Linguistics (Findings of EACL)
  • Year: 2023
  • Subject: Representation Learning, Variational Autoencoders, Explainable and safe AI, Natural Language Processing

• Analysis of business process automation as linear time-invariant system network

  • Authors: Mauricio Jacobo-Romero, Danilo S. Carvalho, Andre Freitas
  • In: (preprint)
  • Year: 2023
  • Subject: Computational Engineering, AI Automation, Productivity, Signal Processing, Process Mining
  • DOI: 10.48550/arXiv.2302.04785

• Quasi-symbolic explanatory NLI via disentanglement: A geometrical examination

  • Authors: Yingji Zhang, Danilo S. Carvalho, Ian Pratt-Hartmann, André Freitas
  • In: (preprint)
  • Year: 2022
  • Subject: Deep Neural models, Explainable and safe AI, Natural Language Inference
  • DOI: 10.48550/arXiv.2210.06230

• Estimating productivity gains in digital automation

  • Authors: Mauricio Jacobo-Romero, Danilo S. Carvalho, Andre Freitas
  • In: (preprint)
  • Year: 2022
  • Subject: AI Automation, Productivity, Signal Processing, Process Mining
  • DOI: 10.48550/arXiv.2210.01252

• Systematicity, Compositionality and Transitivity of Deep NLP Models: a Metamorphic Testing Perspective

  • Authors: Edoardo Manino, Julia Rozanova, Danilo Carvalho, Andre Freitas, Lucas Cordeiro
  • In: Findings of the Association for Computational Linguistics: ACL 2022
  • Year: 2022
  • Subject: Metamorphic Testing, Deep Neural models, Explainable and safe AI, Natural Language Processing
  • DOI: 10.18653/v1/2022.findings-acl.185

• EnnCore: End-to-End Conceptual Guarding of Neural Architectures

  • Authors: Edoardo Manino, Danilo Carvalho, Yi Dong, Julia Rozanova, Xidan Song, Mustafa A. Mustafa, Andre Freitas, Gavin Brown, Mikel Luján, Xiaowei Huang, Lucas Cordeiro
  • In: AAAI's Workshops on Artificial Intelligence Safety (SafeAI)
  • Year: 2022
  • Subject: Explainable and safe AI

• Pattern Identification of Bot Messages for Media Literacy

  • Authors: Eric Ferreira dos Santos, Danilo Silva de Carvalho, Jonice Oliveira
  • In: Proc. of the Brazilian Symposium on Multimedia and the Web
  • Year: 2021
  • Subject: Bot Detection, Social Network Analysis, Natural Language Processing
  • DOI: 10.1145/3470482.3479452

• The Gender Patenting Gap: A Study on the Iberoamerican Countries

  • Authors: Danilo S. Carvalho, Lydia Bares, Kelyane Silva
  • In: Journal of Data and Information Science
  • Year: 2020
  • Subject: Patent statistics
  • DOI: 10.2478/jdis-2020-0025

• Uncovering Social Media Bots: a Transparency-focused Approach

  • Authors: Eric F. dos Santos, Danilo S. Carvalho, Lívia Ruback, Jonice Oliveira
  • In: Companion Proceedings of The 2019 World Wide Web Conference
  • Year: 2019
  • Subject: Bot Detection, Social Network Analysis, Natural Language Processing
  • DOI: 10.1145/3308560.3317599

• WikTDV: Data extraction and vector representation resource for Wiktionary senses

  • Authors: Danilo S. Carvalho, Minh-Le Nguyen
  • In: Proc. of the 9th International Conference on Knowledge and Systems Engineering (KSE) 2017
  • Year: 2017
  • Subject: Term Definition Vector, Vectorial Representation, Natural Language Processing
  • DOI: 10.1109/KSE.2017.8119465

• An Analysis of Majority Voting in Homogeneous Groups for Checkers: Understanding Group Performance through Unbalance

  • Authors: Danilo S. Carvalho, Minh-Le Nguyen, Hiroyuki Iida
  • In: Proc. of Advances in Computer Games (ACG) 2017
  • Year: 2017
  • Subject: Statistical Analysis, Checkers, Computer Games
  • DOI: 10.1007/978-3-319-71649-7_18

• Improving Legal Information Retrieval by Distributional Composition with Term Order Probabilities

  • Authors: Danilo S. Carvalho, Vu Tran, Khanh Van Tran, Minh-Le Nguyen
  • In: Proc. of the 4th Competition on Legal Information Extraction and Entailment (COLIEE) 2017
  • Year: 2017
  • Subject: Legal Text Analysis, Language Modeling, Term Order Probabilities, Natural Language Processing
  • DOI: 10.29007/2xzw

• Efficient Neural-based patent document segmentation with Term Order Probabilities

  • Authors: Danilo S. Carvalho, Minh-Le Nguyen
  • In: Proc. of the 25th European Symposium on Artificial Neural Networks (ESANN) 2017
  • Year: 2017
  • Subject: Document Segmentation, Term Order Probabilities, Artificial Neural Networks, Machine Learning, Natural Language Processing

• Building Lexical Vector Representations from Concept Definitions

  • Authors: Danilo S. Carvalho, Minh-Le Nguyen
  • In: Proc. of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL) 2017
  • Year: 2017
  • Subject: Definitional Semantics, Term Definition Vector, Vectorial Representation, Natural Language Processing
  • DOI: 10.18653/v1/e17-1085

• Lexical to Discourse-level Corpus Modeling for Legal Question Answering

  • Authors: Danilo S. Carvalho, Vu Duc Tran, Khanh Van Tran, Minh-Le Nguyen
  • In: Proc. of the 10th International Workshop on Juris-informatics (JURISIN) 2016
  • Year: 2016
  • Subject: Legal Text Analysis, Language Modeling, Natural Language Processing

• Financial credit analysis via a clustering weightless neural classifier

  • Authors: Douglas O. Cardoso, Danilo S. Carvalho, Daniel S.F. Alves, Diego F.P. Souza, Hugo C.C. Carneiro, Carlos E. Pedreira, Priscila M.V. Lima, Felipe M.G. França
  • In: Neurocomputing
  • Year: 2016
  • Subject: Credit Analysis, Temporal Clustering, Weightless Neural Networks, Machine Learning
  • DOI: 10.1016/j.neucom.2015.06.105

• Lexical-Morphological Modeling for Legal Text Analysis

  • Authors: Danilo S. Carvalho, Minh-Tien Nguyen, Tran Xuan Chien, Minh-Le Nguyen
  • In: New Frontiers in Artificial Intelligence (Lecture Notes in Artificial Intelligence)
  • Year: 2016
  • Subject: Legal Text Analysis, Language Modeling, Natural Language Processing
  • DOI: 10.1007/978-3-319-50953-2

• Easyesa: A low-effort infrastructure for explicit semantic analysis

  • Authors: Danilo S. Carvalho, Çaǧatay Çalli, André Freitas, Edward Curry
  • In: Proc. of the 13th International Semantic Web Conference (ISWC), Posters & Demonstrations Track, Volume 1272
  • Year: 2014
  • Subject: Explicit Semantic Analysis, Vectorial Representation, Natural Language Processing

• Extracting Semantic Information from Patent Claims Using Phrasal Structure Annotations

  • Authors: Danilo S. Carvalho, Felipe M. G. França, Priscila M. V. Lima
  • In: Proc. of the 2014 Brazilian Conference on Intelligent Systems, BRACIS 2014
  • Year: 2014
  • Subject: Semantic Relation Extraction, Patents, Weightless Neural Networks, Natural Language Processing
  • DOI: 10.1109/BRACIS.2014.17

• Credit analysis with a clustering RAM-based neural classifier

  • Authors: Douglas de O. Cardoso, Danilo S. Carvalho, Daniel S. F. Alves, Diego F. P. de Souza, Hugo C. C. Carneiro, Carlos E. Pedreira, Priscila M. V. Lima, Felipe M. G. França
  • In: Proc. of the 22th European Symposium on Artificial Neural Networks, ESANN 2014
  • Year: 2014
  • Subject: Credit Analysis, Temporal Clustering, Weightless Neural Networks, Machine Learning

• Extracting rules from DRASiW's "mental images"

  • Authors: Paulo Coutinho, Hugo C. C. Carneiro, Danilo S. Carvalho, Felipe M. G. França
  • In: Proc. of the 22th European Symposium on Artificial Neural Networks, ESANN 2014
  • Year: 2014
  • Subject: WiSARD, Weightless Neural Networks, Machine Learning

• Online tracking of multiple objects using WiSARD

  • Authors: Rafael L. Carvalho, Danilo S. Carvalho, Priscila M. V. Lima, Félix Mora-Camino, Felipe M. G. França
  • In: Proc. of the 22th European Symposium on Artificial Neural Networks, ESANN 2014
  • Year: 2014
  • Subject: Video Object Tracking, WiSARD, Weightless Neural Networks, Machine Learning

• On the Semantic Representation and Extraction of Complex Category Descriptors

  • Authors: André Freitas, Rafael Vieira, Edward Curry and Danilo S. Carvalho, João Carlos Pereira da Silva
  • In: Proc. of the 19th International Conference on Natural Language Processing and Information Systems (NLDB) 2014
  • Year: 2014
  • Subject: Linked Data, Natural Language Processing
  • DOI: 10.1007/978-3-319-07983-7_6

• B-bleaching: Agile Overtraining Avoidance in the WiSARD Weightless Neural Classifier

  • Authors: Danilo S. Carvalho, Hugo C. C. Carneiro, Felipe M. G. França, Priscila M. V. Lima
  • In: Proc. of the 21st European Symposium on Artificial Neural Networks, ESANN 2013
  • Year: 2013
  • Subject: WiSARD, Weightless Neural Networks, Overtraining Avoidance, Machine Learning

• Graphia: extracting contextual relation graphs from text

  • Authors: Danilo S. Carvalho, André Freitas, João C.P. da Silva
  • In: Proc. of Extended Semantic Web Conference
  • Year: 2013
  • Subject: Semantic Relation Extraction, Linked Data, Natural Language Processing
  • DOI: 10.1007/978-3-642-41242-4_31

• Representing texts as contextualized entity-centric Linked Data graphs

  • Authors: André Freitas, Seán O’Riain, Edward Curry, João C.P. da Silva, Danilo S. Carvalho
  • In: Proc. of Database and Expert Systems Applications (DEXA), 2013 24th International Workshop
  • Year: 2013
  • Subject: Semantic Relation Extraction, Linked Data, Natural Language Processing
  • DOI: 10.1109/DEXA.2013.21

• A semantic best-effort approach for extracting structured discourse graphs from wikipedia

  • Authors: André Freitas, Danilo S. Carvalho, João C.P. da Silva, Seán O’Riain, Edward Curry
  • In: Proc. of the 1st Workshop on the Web of Linked Entities,(ISWC)
  • Year: 2012
  • Subject: Semantic Relation Extraction, Linked Data, Natural Language Processing