Esma Balkir
9 papers · 2019–2023 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (4) π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (18)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
β
The Questioner
Conferences
ACL (3)
NAACL (3)
EMNLP (2)
IJCNLP (1)
Top co-authors
Keywords
concept-based explanation
(2)
negative sampling
(2)
bilinear model
(2)
model interpretability
(2)
link prediction
(2)
bias detection
(2)
knowledge graph completion
(2)
natural language processing
(1)
sentiment analysis
(1)
feature attribution
(1)
abusive language detection
(1)
language model
(1)
latent variable
(1)
entity embedding
(1)
bias mitigation
(1)
text classification
(1)
model explanation
(1)
procedural fairness
(1)
adversarial learning
(1)
model probing
(1)
Papers
Concept-Based Explanations to Test for False Causal Relationships Learned by Abusive Language Classifiers
ACL 2023
This prompt is measuring <mask>: evaluating bias evaluation in language models
ACL 2023
Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models
NAACL 2022
Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information
EMNLP 2022
Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech Detection
NAACL 2022
Does Moral Code have a Moral Code? Probing Delphiβs Moral Philosophy
NAACL 2022
Tensors over Semirings for Latent-Variable Weighted Logic Programs
ACL 2020
Using Pairwise Occurrence Information to Improve Knowledge Graph Completion on Large-Scale Datasets
EMNLP 2019
Using Pairwise Occurrence Information to Improve Knowledge Graph Completion on Large-Scale Datasets
IJCNLP 2019