← Authors

Pierre Colombo

35 papers · 2018–2025 · 9 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (9) πŸƒ Academic Marathon (7) 🌈 Renaissance Researcher (8) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (71) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸ† Keyword Champion (3) 🀝 Dynamic Duo (14) 🧬 Topic Evolution πŸ‘₯ Mega-Team (54) πŸ’Ž Century Club (35) πŸ”₯ Unstoppable (8) πŸ—ƒοΈ Keyword Collector (165) ❓ The Questioner (2) ⚑ Prolific Year (5)

Conferences

EMNLP (16) NIPS (5) IJCNLP (4) ACL (3) AAAI (2) AACL (2) COLING (1) ICLR (1) NAACL (1)

Top co-authors

Pablo Piantanida (14) ChloΓ© Clavel (12) Nathan Noiry (9) Guillaume Staerman (8) Emile Chapuis (4) Celine Hudelot (4) Matthieu Labeau (4) Manuel Faysse (3) Nuno M. Guerreiro (3) Gautier Viaud (3)

Keywords

large language model (4) out-of-distribution detection (3) fair classification (3) contextual embedding (3) disentangled representation (3) representation learning (3) text classification (3) unsupervised learning (3) ranking aggregation (2) benchmark evaluation (2) renyi divergence (2) mutual information (2) variational inference (2) hierarchical model (2) optimal transport (2) multimodal learning (2) machine translation (2) attention mechanism (2) preference alignment (2) opinion mining (2)

Papers

ColPali: Efficient Document Retrieval with Vision Language Models ICLR 2025
Context is Gold to find the Gold Passage: Evaluating and Training Contextual Document Embeddings EMNLP 2025
Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysis EMNLP 2024
SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain NIPS 2024
Unsupervised Layer-Wise Score Aggregation for Textual OOD Detection AAAI 2024
Enhanced Hallucination Detection in Neural Machine Translation through Simple Detector Aggregation EMNLP 2024
Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarks EMNLP 2024
The Glass Ceiling of Automatic Evaluation in Natural Language Generation AACL 2023
A Novel Information Theoretic Objective to Disentangle Representations for Fair Classification AACL 2023
Optimal Transport for Unsupervised Hallucination Detection in Neural Machine Translation ACL 2023
A Novel Information Theoretic Objective to Disentangle Representations for Fair Classification IJCNLP 2023
The Glass Ceiling of Automatic Evaluation in Natural Language Generation IJCNLP 2023
Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models EMNLP 2023
RainProof: An Umbrella to Shield Text Generator from Out-Of-Distribution Data EMNLP 2023
Revisiting Instruction Fine-tuned Model Evaluation to Guide Industrial Applications EMNLP 2023
Toward Stronger Textual Attack Detectors EMNLP 2023
Steering Large Language Models for Machine Translation with Finetuning and In-Context Learning EMNLP 2023
The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset NIPS 2022
Learning Disentangled Textual Representations via Statistical Measures of Similarity ACL 2022
Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation COLING 2022
Beyond Mahalanobis Distance for Textual OOD Detection NIPS 2022
What are the best Systems? New Perspectives on NLP Benchmarking NIPS 2022
A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations IJCNLP 2021
Code-switched inspired losses for spoken dialog representations EMNLP 2021
A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations ACL 2021
Improving Multimodal fusion via Mutual Dependency Maximisation EMNLP 2021
Automatic Text Evaluation through the Lens of Wasserstein Barycenters EMNLP 2021
Heavy-tailed Representations, Text Polarity Classification & Data Augmentation NIPS 2020
Guiding Attention in Sequence-to-Sequence Models for Dialogue Act Prediction AAAI 2020
The importance of fillers for text representations of speech transcripts EMNLP 2020
Hierarchical Pre-training for Sequence Labelling in Spoken Dialog EMNLP 2020
From the Token to the Review: A Hierarchical Multimodal approach to Opinion Mining IJCNLP 2019
From the Token to the Review: A Hierarchical Multimodal approach to Opinion Mining EMNLP 2019
Affect-Driven Dialog Generation NAACL 2019
Disney at IEST 2018: Predicting Emotions using an Ensemble EMNLP 2018