


default search action
André Freitas
Person information
Refine list

refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2025
- [c134]Danilo Silva de Carvalho, Edoardo Manino, Julia Rozanova, Lucas C. Cordeiro, André Freitas:
Montague semantics and modifier consistency measurement in neural language models. COLING 2025: 5515-5529 - 2024
- [j19]Xiaowei Huang, Wenjie Ruan, Wei Huang, Gaojie Jin, Yi Dong, Changshun Wu, Saddek Bensalem, Ronghui Mu, Yi Qi, Xingyu Zhao, Kaiwen Cai, Yanghao Zhang, Sihao Wu, Peipei Xu, Dengyu Wu
, André Freitas, Mustafa A. Mustafa:
A survey of safety and trustworthiness of large language models through the lens of verification and validation. Artif. Intell. Rev. 57(7): 175 (2024) - [j18]Magdalena Wysocka
, Oskar Wysocki, Maxime Delmas, Vincent Mutel, André Freitas:
Large Language Models, scientific knowledge and factuality: A framework to streamline human expert evaluation. J. Biomed. Informatics 158: 104724 (2024) - [c133]Dhairya Dalal, Marco Valentino, André Freitas, Paul Buitelaar:
Inference to the Best Explanation in Large Language Models. ACL (1) 2024: 217-235 - [c132]Yingji Zhang, Danilo Carvalho, André Freitas:
Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networks. ACL (1) 2024: 2113-2134 - [c131]Leonardo Ranaldi, Giulia Pucci, André Freitas:
Empowering cross-lingual abilities of instruction-tuned large language models by translation-following demonstrations. ACL (Findings) 2024: 7961-7973 - [c130]Mokanarangan Thayaparan, Marco Valentino, André Freitas:
A Differentiable Integer Linear Programming Solver for Explanation-Based Natural Language Inference. LREC/COLING 2024: 449-458 - [c129]Julia Rozanova, Marco Valentino, André Freitas:
Estimating the Causal Effects of Natural Logic Features in Transformer-Based NLI Models. LREC/COLING 2024: 6319-6329 - [c128]Xin Quan, Marco Valentino, Louise A. Dennis, André Freitas:
Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement. EACL (1) 2024: 1-22 - [c127]Marco Valentino, Danilo S. Carvalho, André Freitas:
Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions. EACL (1) 2024: 23-34 - [c126]Yingji Zhang, Danilo S. Carvalho, Marco Valentino, Ian Pratt-Hartmann, André Freitas:
Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders. EACL (Findings) 2024: 1434-1450 - [c125]Leonardo Ranaldi, André Freitas:
Aligning Large and Small Language Models via Chain-of-Thought Reasoning. EACL (1) 2024: 1812-1827 - [c124]Hafiz Tayyab Rauf, André Freitas, Norman W. Paton:
Deep Clustering for Data Cleaning and Integration. EDBT 2024: 636-649 - [c123]Leonardo Ranaldi, André Freitas:
Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models. EMNLP 2024: 2325-2347 - [c122]Xin Quan, Marco Valentino, Louise A. Dennis, André Freitas:
Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving. EMNLP 2024: 2933-2958 - [c121]Lan Zhang, Xin Quan, André Freitas:
Consistent Autoformalization for Constructing Mathematical Libraries. EMNLP 2024: 4020-4033 - [c120]Jordan Meadows, Tamsin James, André Freitas:
Exploring the Limits of Fine-grained LLM-based Physics Inference via Premise Removal Interventions. EMNLP (Findings) 2024: 6487-6502 - [c119]Yingji Zhang, Marco Valentino, Danilo S. Carvalho, Ian Pratt-Hartmann, André Freitas:
Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoders. NAACL-HLT (Findings) 2024: 474-489 - [c118]Marco Valentino, Jordan Meadows, Lan Zhang, André Freitas:
Multi-Operational Mathematical Derivations in Latent Space. NAACL-HLT 2024: 1446-1458 - [c117]Jordan Meadows, Marco Valentino, Damien Teney, André Freitas:
A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers. NAACL-HLT 2024: 1505-1523 - [c116]Giangiacomo Mercatali, André Freitas, Jie Chen:
Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Series. NeurIPS 2024 - [c115]Maël Jullien, Marco Valentino, André Freitas:
SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials. SemEval@NAACL 2024: 1947-1962 - [d4]Maxime Delmas
, Magdalena Wysocka, André Freitas
:
Synthetic dataset for end-to-end Relation Extraction of relationships between Organisms and Natural-Products with Mixtral-8x7B-Instruct-v0.1. Zenodo, 2024 - [i109]Yingji Zhang, Danilo S. Carvalho, Marco Valentino, Ian Pratt-Hartmann, André Freitas:
Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders. CoRR abs/2402.00723 (2024) - [i108]Xin Quan, Marco Valentino, Louise A. Dennis, André Freitas:
Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement. CoRR abs/2402.00745 (2024) - [i107]Dhairya Dalal, Marco Valentino, André Freitas, Paul Buitelaar:
Inference to the Best Explanation in Large Language Models. CoRR abs/2402.10767 (2024) - [i106]Julia Rozanova, Marco Valentino, André Freitas:
Estimating the Causal Effects of Natural Logic Features in Transformer-Based NLI Models. CoRR abs/2404.02622 (2024) - [i105]Mokanarangan Thayaparan, Marco Valentino, André Freitas:
A Differentiable Integer Linear Programming Solver for Explanation-Based Natural Language Inference. CoRR abs/2404.02625 (2024) - [i104]Maël Jullien, Marco Valentino, André Freitas:
SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials. CoRR abs/2404.04963 (2024) - [i103]Jordan Meadows, Tamsin James, André Freitas:
Exploring the Limits of Fine-grained LLM-based Physics Inference via Premise Removal Interventions. CoRR abs/2404.18384 (2024) - [i102]Leonardo Ranaldi, André Freitas:
Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models. CoRR abs/2405.00402 (2024) - [i101]Xin Quan, Marco Valentino, Louise A. Dennis, André Freitas:
Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving. CoRR abs/2405.01379 (2024) - [i100]Hafiz Tayyab Rauf, André Freitas, Norman W. Paton:
TableDC: Deep Clustering for Tabular Data. CoRR abs/2405.17723 (2024) - [i99]Oskar Wysocki, Magdalena Wysocka, Danilo Carvalho, Alex Teodor Bogatu, Danilo Miranda Gusicuma, Maxime Delmas, Harriet Unsworth, André Freitas:
An LLM-based Knowledge Synthesis and Scientific Reasoning Framework for Biomedical Discovery. CoRR abs/2406.18626 (2024) - [i98]Geonhee Kim, Marco Valentino, André Freitas:
A Mechanistic Interpretation of Syllogistic Reasoning in Auto-Regressive Language Models. CoRR abs/2408.08590 (2024) - [i97]Nura Aljaafari
, Danilo S. Carvalho, André Freitas:
The Mechanics of Conceptual Interpretation in GPT Models: Interpretative Insights. CoRR abs/2408.11827 (2024) - [i96]João Pedro Gandarela, Danilo S. Carvalho, André Freitas:
Inductive Learning of Logical Theories with LLMs: A Complexity-graded Analysis. CoRR abs/2408.16779 (2024) - [i95]Maël Jullien, Alex Teodor Bogatu, Harriet Unsworth, André Freitas:
Controlled LLM-based Reasoning for Clinical Trial Retrieval. CoRR abs/2409.18998 (2024) - [i94]Marco Valentino, André Freitas:
Reasoning with Natural Language Explanations. CoRR abs/2410.04148 (2024) - [i93]Lan Zhang, Xin Quan, André Freitas:
Consistent Autoformalization for Constructing Mathematical Libraries. CoRR abs/2410.04194 (2024) - [i92]Hafiz Tayyab Rauf, Alex Bogatu, Norman W. Paton, André Freitas:
Gem: Gaussian Mixture Model Embeddings for Numerical Feature Distributions. CoRR abs/2410.07485 (2024) - [i91]Nura Aljaafari, Danilo S. Carvalho, André Freitas:
Interpreting token compositionality in LLMs: A robustness analysis. CoRR abs/2410.12924 (2024) - [i90]Giangiacomo Mercatali, André Freitas, Jie Chen:
Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Series. CoRR abs/2410.14030 (2024) - [i89]Magdalena Wysocka, Danilo S. Carvalho, Oskar Wysocki, Marco Valentino, André Freitas:
SylloBio-NLI: Evaluating Large Language Models on Biomedical Syllogistic Reasoning. CoRR abs/2410.14399 (2024) - [i88]Leonardo Ranaldi, Marco Valentino, André Freitas:
Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations. CoRR abs/2410.22874 (2024) - [i87]Giangiacomo Mercatali, Yogesh Verma, André Freitas, Vikas Garg:
Diffusion Twigs with Loop Guidance for Conditional Graph Generation. CoRR abs/2410.24012 (2024) - 2023
- [j17]Oskar Wysocki
, Jessica Katharine Davies, Markel Vigo, Anne Caroline Armstrong, Dónal Landers
, Rebecca Lee
, André Freitas
:
Assessing the communication gap between AI models and healthcare professionals: Explainability, utility and trust in AI-driven clinical decision-making. Artif. Intell. 316: 103839 (2023) - [j16]Magdalena Wysocka, Oskar Wysocki
, Marie Zufferey, Dónal Landers, André Freitas:
A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data. BMC Bioinform. 24(1): 198 (2023) - [j15]Oskar Wysocki
, Zili Zhou, Paul O'Regan, Deborah Ferreira, Magdalena Wysocka, Dónal Landers, André Freitas:
Transformers and the Representation of Biomedical Background Knowledge. Comput. Linguistics 49(1): 73-115 (2023) - [j14]Alex Bogatu
, Magdalena Wysocka, Oskar Wysocki
, Holly Butterworth, Manon Pillai, Jennifer Allison, Dónal Landers, Elaine Kilgour, Fiona Thistlethwaite
, André Freitas:
Meta-analysis informed machine learning: Supporting cytokine storm detection during CAR-T cell Therapy. J. Biomed. Informatics 142: 104367 (2023) - [j13]Christina Niklaus, Matthias Cetto, André Freitas, Siegfried Handschuh
:
A Canonical Context-Preserving Representation for Open IE: Extracting Semantically Typed Relational Tuples from Complex Sentences. Knowl. Based Syst. 268: 110455 (2023) - [j12]Jordan Meadows, André Freitas:
Introduction to Mathematical Language Processing: Informal Proofs, Word Problems, and Supporting Tasks. Trans. Assoc. Comput. Linguistics 11: 1162-1184 (2023) - [c114]Leonardo Ranaldi, Giulia Pucci, Elena Sofia Ruzzetti, Fabio Massimo Zanzotto, André Freitas:
Teasing LLMs Adapted to Italian. CLiC-it 2023 - [c113]Danilo Silva de Carvalho, Giangiacomo Mercatali, Yingji Zhang, André Freitas:
Learning Disentangled Representations for Natural Language Definitions. EACL (Findings) 2023: 1341-1354 - [c112]Julia Rozanova
, Marco Valentino
, Lucas C. Cordeiro
, André Freitas
:
Interventional Probing in High Dimensions: An NLI Case Study. EACL (Findings) 2023: 2444-2455 - [c111]Maël Jullien, Marco Valentino, Hannah Frost, Paul O'Regan, Dónal Landers, André Freitas:
NLI4CT: Multi-Evidence Natural Language Inference for Clinical Trial Reports. EMNLP 2023: 16745-16764 - [c110]André Freitas
, Francisco Fernandes
, Mara Dionísio
, Sandra Câmara Olim
:
Mystery in the Ecological Park: An Interactive Narrative to Promote Interaction with Biodiversity. ICEC 2023: 360-364 - [c109]Mario Ramirez, Alex Bogatu, Norman W. Paton, André Freitas
:
Transformers, Tables and Frame Semantics. ICSC 2023: 155-160 - [c108]Maël Jullien, Marco Valentino, Hannah Frost, Paul O'Regan, Donal Landers, André Freitas:
SemEval-2023 Task 7: Multi-Evidence Natural Language Inference for Clinical Trial Data. SemEval@ACL 2023: 2216-2226 - [d3]Maxime Delmas
, Magdalena Wysocka, André Freitas
:
Synthetic datasets for end-to-end Relation Extraction of relationships between Organisms and Natural-Products. Zenodo, 2023 - [d2]Maxime Delmas
, Magdalena Wysocka, André Freitas
:
Synthetic dataset for end-to-end Relation Extraction of relationships between Organisms and Natural-Products with Vicuna-13b-v1.5. Zenodo, 2023 - [d1]Magdalena Wysocka, Maxime Delmas
, André Freitas
:
Evaluation dataset for Relation Extraction of relationships between Organisms and Natural-Products. Zenodo, 2023 - [i86]Mauricio Jacobo-Romero, Danilo S. Carvalho, André Freitas
:
Analysis of business process automation as linear time-invariant system network. CoRR abs/2302.04785 (2023) - [i85]Hanadi Mardah, Oskar Wysocki, Markel Vigo, André Freitas
:
On the Visualisation of Argumentation Graphs to Support Text Interpretation. CoRR abs/2303.03235 (2023) - [i84]Julia Rozanova, Marco Valentino, Lucas C. Cordeiro, André Freitas:
Interventional Probing in High Dimensions: An NLI Case Study. CoRR abs/2304.10346 (2023) - [i83]Yingji Zhang, Danilo S. Carvalho, Ian Pratt-Hartmann, André Freitas:
Learning Disentangled Semantic Spaces of Explanations via Invertible Neural Networks. CoRR abs/2305.01713 (2023) - [i82]Maël Jullien, Marco Valentino, Hannah Frost, Paul O'Regan, Donal Landers, André Freitas:
SemEval-2023 Task 7: Multi-Evidence Natural Language Inference for Clinical Trial Data. CoRR abs/2305.02993 (2023) - [i81]Maël Jullien, Marco Valentino, Hannah Frost, Paul O'Regan, Donal Landers, André Freitas:
NLI4CT: Multi-Evidence Natural Language Inference for Clinical Trial Reports. CoRR abs/2305.03598 (2023) - [i80]Marco Valentino, Danilo S. Carvalho, André Freitas:
Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions. CoRR abs/2305.07303 (2023) - [i79]Julia Rozanova, Marco Valentino, André Freitas:
Estimating the Causal Effects of Natural Logic Features in Neural NLI Models. CoRR abs/2305.08572 (2023) - [i78]Xiaowei Huang, Wenjie Ruan, Wei Huang, Gaojie Jin, Yi Dong
, Changshun Wu, Saddek Bensalem, Ronghui Mu, Yi Qi, Xingyu Zhao, Kaiwen Cai, Yanghao Zhang, Sihao Wu, Peipei Xu, Dengyu Wu
, André Freitas, Mustafa A. Mustafa:
A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation. CoRR abs/2305.11391 (2023) - [i77]Jordan Meadows, Marco Valentino, Damien Teney, André Freitas:
A Symbolic Framework for Systematic Evaluation of Mathematical Reasoning with Transformers. CoRR abs/2305.12563 (2023) - [i76]Hafiz Tayyab Rauf, Norman W. Paton, André Freitas:
Deep Clustering for Data Cleaning and Integration. CoRR abs/2305.13494 (2023) - [i75]Magdalena Wysocka, Oskar Wysocki, Maxime Delmas, Vincent Mutel, André Freitas:
Large Language Models, scientific knowledge and factuality: A systematic analysis in antibiotic discovery. CoRR abs/2305.17819 (2023) - [i74]Jordan Meadows, Marco Valentino, André Freitas:
Generating Mathematical Derivations with Large Language Models. CoRR abs/2307.09998 (2023) - [i73]Christina Niklaus, Matthias Cetto, André Freitas, Siegfried Handschuh
:
Discourse-Aware Text Simplification: From Complex Sentences to Linked Propositions. CoRR abs/2308.00425 (2023) - [i72]Yingji Zhang, Danilo S. Carvalho, Ian Pratt-Hartmann, André Freitas:
Towards Controllable Natural Language Inference through Lexical Inference Types. CoRR abs/2308.03581 (2023) - [i71]Leonardo Ranaldi
, Giulia Pucci, André Freitas:
Empowering Cross-lingual Abilities of Instruction-tuned Large Language Models by Translation-following demonstrations. CoRR abs/2308.14186 (2023) - [i70]Marco Valentino, Jordan Meadows, Lan Zhang, André Freitas:
Multi-Operational Mathematical Derivations in Latent Space. CoRR abs/2311.01230 (2023) - [i69]Maxime Delmas, Magdalena Wysocka, André Freitas:
Relation Extraction in underexplored biomedical domains: A diversity-optimised sampling and synthetic data generation approach. CoRR abs/2311.06364 (2023) - [i68]Yingji Zhang, Marco Valentino, Danilo S. Carvalho, Ian Pratt-Hartmann, André Freitas:
Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoders. CoRR abs/2311.08579 (2023) - [i67]Yingji Zhang, Danilo S. Carvalho, Ian Pratt-Hartmann, André Freitas:
LlaMaVAE: Guiding Large Language Model Generation via Continuous Latent Sentence Spaces. CoRR abs/2312.13208 (2023) - 2022
- [j11]Philip Osborne, Heido Nõmm, André Freitas
:
A Survey of Text Games for Reinforcement Learning Informed by Natural Language. Trans. Assoc. Comput. Linguistics 10: 873-887 (2022) - [j10]Mokanarangan Thayaparan, Marco Valentino, Deborah Ferreira, Julia Rozanova, André Freitas
:
Diff-Explainer: Differentiable Convex Optimization for Explainable Multi-hop Inference. Trans. Assoc. Comput. Linguistics 10: 1103-1119 (2022) - [c107]Edoardo Manino, Danilo S. Carvalho, Yi Dong, Julia Rozanova, Xidan Song, Mustafa A. Mustafa, André Freitas, Gavin Brown, Mikel Luján, Xiaowei Huang, Lucas C. Cordeiro:
EnnCore: End-to-End Conceptual Guarding of Neural Architectures. SafeAI@AAAI 2022 - [c106]Marco Valentino, Mokanarangan Thayaparan, Deborah Ferreira, André Freitas
:
Hybrid Autoregressive Inference for Scalable Multi-Hop Explanation Regeneration. AAAI 2022: 11403-11411 - [c105]Deborah Ferreira, Mokanarangan Thayaparan, Marco Valentino, Julia Rozanova, André Freitas
:
To be or not to be an Integer? Encoding Variables for Mathematical Text. ACL (Findings) 2022: 938-948 - [c104]Edoardo Manino
, Julia Rozanova, Danilo S. Carvalho, André Freitas
, Lucas C. Cordeiro:
Systematicity, Compositionality and Transitivity of Deep NLP Models: a Metamorphic Testing Perspective. ACL (Findings) 2022: 2355-2366 - [c103]Julia Rozanova, Deborah Ferreira, Mokanarangan Thayaparan, Marco Valentino, André Freitas
:
Decomposing Natural Logic Inferences for Neural NLI. BlackboxNLP@EMNLP 2022: 394-403 - [c102]Marco Valentino, Mokanarangan Thayaparan, André Freitas
:
Case-Based Abductive Natural Language Inference. COLING 2022: 1556-1568 - [c101]Guy Clarke Marshall, Caroline Jay, André Freitas:
Why Scholars Are Diagramming Neural Network Models. Diagrams 2022: 202-209 - [c100]Alex Bogatu, Norman W. Paton, Mark Douthwaite, André Freitas
:
Voyager: Data Discovery and Integration for Onboarding in Data Science. EDBT 2022: 2:537-2:548 - [c99]Jordan Meadows, Zili Zhou, André Freitas
:
PhysNLU: A Language Resource for Evaluating Natural Language Understanding and Explanation Coherence in Physics. LREC 2022: 4611-4619 - [c98]Minh-Quoc Nghiem, Paul Baylis, André Freitas
, Sophia Ananiadou:
Text Classification and Prediction in the Legal Domain. LREC 2022: 4717-4722 - [c97]Giangiacomo Mercatali, André Freitas, Vikas Garg:
Symmetry-induced Disentanglement on Graphs. NeurIPS 2022 - [i66]Jordan Meadows, Zili Zhou, André Freitas:
PhysNLU: A Language Resource for Evaluating Natural Language Understanding and Explanation Coherence in Physics. CoRR abs/2201.04275 (2022) - [i65]Mauricio Jacobo-Romero, André Freitas:
Microeconomic Foundations of Decentralised Organisations. CoRR abs/2201.07666 (2022) - [i64]Maël Jullien, Marco Valentino, André Freitas:
Do Transformers Encode a Foundational Ontology? Probing Abstract Classes in Natural Language. CoRR abs/2201.10262 (2022) - [i63]Oskar Wysocki, Zili Zhou, Paul O'Regan, Deborah Ferreira, Magdalena Wysocka, Donal Landers
, André Freitas
:
Transformers and the representation of biomedical background knowledge. CoRR abs/2202.02432 (2022) - [i62]Oskar Wysocki
, Jessica Katharine Davies, Markel Vigo, Anne Caroline Armstrong, Dónal Landers, Rebecca Lee, André Freitas
:
Assessing the communication gap between AI models and healthcare professionals: explainability, utility and trust in AI-driven clinical decision-making. CoRR abs/2204.05030 (2022) - [i61]Edoardo Manino, Julia Rozanova, Danilo S. Carvalho, André Freitas
, Lucas C. Cordeiro:
Systematicity, Compositionality and Transitivity of Deep NLP Models: a Metamorphic Testing Perspective. CoRR abs/2204.12316 (2022) - [i60]Marco Valentino, André Freitas
:
Scientific Explanation and Natural Language: A Unified Epistemological-Linguistic Perspective for Explainable AI. CoRR abs/2205.01809 (2022) - [i59]Jordan Meadows, André Freitas
:
A Survey in Mathematical Language Processing. CoRR abs/2205.15231 (2022) - [i58]Alex Bogatu, Magdalena Wysocka, Oskar Wysocki
, Holly Butterworth, Donal Landers, Elaine Kilgour, André Freitas
:
Metareview-informed Explainable Cytokine Storm Detection during CAR-T cell Therapy. CoRR abs/2206.10612 (2022) - [i57]Magdalena Wysocka, Oskar Wysocki
, Marie Zufferey, Dónal Landers, André Freitas
:
Biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data. CoRR abs/2207.00812 (2022) - [i56]Alex Bogatu, Zili Zhou, Dónal Landers, André Freitas
:
Active entailment encoding for explanation tree construction using parsimonious generation of hard negatives. CoRR abs/2208.01376 (2022) - [i55]Mokanarangan Thayaparan, Marco Valentino, André Freitas
:
Going Beyond Approximation: Encoding Constraints for Explainable Multi-hop Inference via Differentiable Combinatorial Solvers. CoRR abs/2208.03339 (2022) - [i54]Mauricio Jacobo-Romero, Danilo S. Carvalho, André Freitas
:
Estimating productivity gains in digital automation. CoRR abs/2210.01252 (2022) - [i53]Danilo S. Carvalho, Giangiacomo Mercatali, Yingji Zhang, André Freitas
:
Learning Disentangled Representations for Natural Language Definitions. CoRR abs/2210.02898 (2022) - [i52]Yingji Zhang, Danilo S. Carvalho, Ian Pratt-Hartmann, André Freitas
:
Quasi-symbolic explanatory NLI via disentanglement: A geometrical examination. CoRR abs/2210.06230 (2022) - [i51]Danilo S. Carvalho, Edoardo Manino, Julia Rozanova, Lucas C. Cordeiro, André Freitas
:
Montague semantics and modifier consistency measurement in neural language models. CoRR abs/2212.04310 (2022) - 2021
- [c96]Mokanarangan Thayaparan, Marco Valentino, André Freitas
:
Explainable Inference Over Grounding-Abstract Chains for Science Questions. ACL/IJCNLP (Findings) 2021: 1-12 - [c95]Deborah Ferreira, Julia Rozanova, Mokanarangan Thayaparan, Marco Valentino, André Freitas
:
Does My Representation Capture X? Probe-Ably. ACL (demo) 2021: 194-201 - [c94]Guy Clarke Marshall
, Caroline Jay
, André Freitas
:
Understanding Scholarly Neural Network System Diagrams Through Application of VisDNA. Diagrams 2021: 387-394 - [c93]