Paulo Cavalin
11 papers · 2020–2026 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Conference Polyglot (7) π Academic Marathon (5) π Renaissance Researcher (6) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (32)
πΊοΈ
Taxonomy Completionist
(32)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π
Keyword Champion
(3)
ποΈ
Keyword Collector
(54)
π
Century Club
(10)
Conferences
AAAI (2)
ACL (2)
COLING (2)
EMNLP (2)
IJCAI (1)
IJCNLP (1)
NAACL (1)
Top co-authors
Research topics
Keywords
out-of-scope detection
(3)
intent classification
(2)
text classification
(2)
indigenous language
(2)
machine translation
(2)
semantic similarity
(2)
conversational system
(2)
neuro-symbolic algorithm
(2)
intent recognition
(2)
responsible ai
(1)
low-resource language
(1)
embedding learning
(1)
text embedding
(1)
transformer neural network
(1)
taxonomy embedding
(1)
one-hot encoding
(1)
graph embedding
(1)
sequence-to-sequence model
(1)
multilingual text classification
(1)
model reliability
(1)
Papers
Small Models Exhibit Limited Answer Consistency in Repetition Trials of the Multiple-Choice MMLU-Redux and MedQA Benchmarks
AAAI 2026
Sentence-level Aggregation of Lexical Metrics Correlates Stronger with Human Judgements than Corpus-level Aggregation
AAAI 2025
Theoretical and Empirical Advantages of Dense-Vector to One-Hot Encoding of Intent Classes in Open-World Scenarios
COLING 2024
Quantifying the Ethical Dilemma of Using Culturally Toxic Training Data in AI Tools for Indigenous Languages
COLING 2024
Fixing Rogue Memorization in Many-to-One Multilingual Translators of Extremely-Low-Resource Languages by Rephrasing Training Samples
NAACL 2024
Balancing Social Impact, Opportunities, and Ethical Constraints of Using AI in the Documentation and Vitalization of Indigenous Languages
IJCAI 2023
Understanding Native Language Identification for Brazilian Indigenous Languages
ACL 2023
Using Meta-Knowledge Mined from Identifiers to Improve Intent Recognition in Conversational Systems
ACL 2021
Using Meta-Knowledge Mined from Identifiers to Improve Intent Recognition in Conversational Systems
IJCNLP 2021
From Disjoint Sets to Parallel Data to Train Seq2Seq Models for Sentiment Transfer
EMNLP 2020
Improving Out-of-Scope Detection in Intent Classification by Using Embeddings of the Word Graph Space of the Classes
EMNLP 2020