05.12.2023
MCML at EMNLP 2023
17 Accepted Papers (9 Main, 7 Findings, and 1 Workshop)
Conference on Empirical Methods in Natural Language Processing, Singapore, Dec 06-10, 2023
We are happy to announce that MCML researchers have contributed a total of 17 papers to EMNLP 2023: 9 Main, 7 Findings, and 1 Workshop papers. Congrats to our researchers!
Main Track (9 papers)
A Study on Accessing Linguistic Information in Pre-Trained Language Models by Using Prompts.
EMNLP 2023 - Conference on Empirical Methods in Natural Language Processing. Singapore, Dec 06-10, 2023. DOI
What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability.
EMNLP 2023 - Conference on Empirical Methods in Natural Language Processing. Singapore, Dec 06-10, 2023. DOI
Automatic transcription of handwritten Old Occitan language.
EMNLP 2023 - Conference on Empirical Methods in Natural Language Processing. Singapore, Dec 06-10, 2023. DOI
Language Models with Rationality.
EMNLP 2023 - Conference on Empirical Methods in Natural Language Processing. Singapore, Dec 06-10, 2023. DOI
Establishing Trustworthiness: Rethinking Tasks and Model Evaluation.
EMNLP 2023 - Conference on Empirical Methods in Natural Language Processing. Singapore, Dec 06-10, 2023. DOI
GradSim: Gradient-Based Language Grouping for Effective Multilingual Training.
EMNLP 2023 - Conference on Empirical Methods in Natural Language Processing. Singapore, Dec 06-10, 2023. DOI
Counting the Bugs in ChatGPT's Wugs: A Multilingual Investigation into the Morphological Capabilities of a Large Language Model.
EMNLP 2023 - Conference on Empirical Methods in Natural Language Processing. Singapore, Dec 06-10, 2023. DOI
ACTOR: Active Learning with Annotator-specific Classification Heads to Embrace Human Label Variation.
EMNLP 2023 - Conference on Empirical Methods in Natural Language Processing. Singapore, Dec 06-10, 2023. DOI
From Dissonance to Insights: Dissecting Disagreements in Rationale Construction for Case Outcome Classification.
EMNLP 2023 - Conference on Empirical Methods in Natural Language Processing. Singapore, Dec 06-10, 2023. DOI
Findings Track (7 papers)
GlotLID: Language Identification for Low-Resource Languages.
Findings @EMNLP 2023 - Findings of the Conference on Empirical Methods in Natural Language Processing. Singapore, Dec 06-10, 2023. DOI GitHub
MEAL: Stable and Active Learning for Few-Shot Prompting.
Findings @EMNLP 2023 - Findings of the Conference on Empirical Methods in Natural Language Processing. Singapore, Dec 06-10, 2023. DOI GitHub
Language-Agnostic Bias Detection in Language Models with Bias Probing.
Findings @EMNLP 2023 - Findings of the Conference on Empirical Methods in Natural Language Processing. Singapore, Dec 06-10, 2023. DOI GitHub
Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translation.
Findings @EMNLP 2023 - Findings of the Conference on Empirical Methods in Natural Language Processing. Singapore, Dec 06-10, 2023. DOI
Crosslingual Transfer Learning for Low-Resource Languages Based on Multilingual Colexification Graphs.
Findings @EMNLP 2023 - Findings of the Conference on Empirical Methods in Natural Language Processing. Singapore, Dec 06-10, 2023. DOI
Subspace Chronicles: How Linguistic Information Emerges, Shifts and Interacts during Language Model Training.
Findings @EMNLP 2023 - Findings of the Conference on Empirical Methods in Natural Language Processing. Singapore, Dec 06-10, 2023. DOI
Unleashing the Multilingual Encoder Potential: Boosting Zero-Shot Performance via Probability Calibration.
Findings @EMNLP 2023 - Findings of the Conference on Empirical Methods in Natural Language Processing. Singapore, Dec 06-10, 2023. DOI
Workshops (1 paper)
Multilingual Word Embeddings for Low-Resource Languages using Anchors and a Chain of Related Languages.
MRL @EMNLP 2023 - 3rd Workshop on Multi-lingual Representation Learning at the Conference on Empirical Methods in Natural Language Processing. Singapore, Dec 06-10, 2023. DOI
Related
22.07.2026
MCML Welcomes Student Delegation From HEC Montréal
MCML welcomed students from HEC Montréal for discussions on AI research, ethics, and international academic collaboration.
21.07.2026
Timo Heiß Receives Best Student Paper Award at XAI 2026
Timo Heiß receives the Best Student Paper Award at XAI 2026 for research on improving feature effect estimation in explainable AI.
21.07.2026
The Learning Rate Does More Than Set the Pace
New ICML 2026 research by Gitta Kutyniok and her team shows how learning rates balance competing biases that shape neural network generalization.