Papers by Géraldine Damnati

7 papers
DivMerge: A divergence-based model merging method for multi-tasking (2026.eacl-long)

Copied to clipboard

Challenge: Existing methods for multitask learning struggle with interference between tasks, especially as the number of tasks grows.
Approach: They propose a reference-free method that minimizes the divergence between models' outputs and those of the merged model, automatically balancing task importance.
Outcome: The proposed method outperforms existing methods on classification and generative tasks and remains robust when scaling to more tasks.
Question Generation and Answering for exploring Digital Humanities collections (2022.lrec-1)

Copied to clipboard

Challenge: Recent advances in representation learning of text have achieved impressive results on benchmark Natural Language Understanding (NLU) tasks.
Approach: They propose a question answering paradigm that uses a BART Transformer based generative model to generate question data.
Outcome: The proposed approach is validated on a new corpus of digitized archive collections of a French Social Science journal.
Handling Normalization Issues for Part-of-Speech Tagging of Online Conversational Text (L18-1)

Copied to clipboard

Challenge: a new approach to POS tagging noisy user generated text is proposed . word embeddings are trained on a noisy corpus to address both normalization and POS.
Approach: They propose to use word embeddings to normalize text before tagging it, while a gated neural network based tagger handles the remaining errors.
Outcome: The proposed approach normalizes some errors before tagging, while a gated neural network handles the remaining errors.
A linguistically-motivated evaluation methodology for unraveling model’s abilities in reading comprehension tasks (2024.emnlp-main)

Copied to clipboard

Challenge: Existing models fail for linguistic characteristics of input examples, despite the impressive quantity of scientific studies dedicated to them, the capabilities, limitations, and risks of these models remain largely unknown.
Approach: They propose to use semantic frame annotation to characterize examples by a small number of complexity factors to account for model’s difficulty.
Outcome: The proposed evaluation methodology is based on the intuition that certain examples consistently yield lower scores regardless of model size or architecture.
Robust Semantic Parsing with Adversarial Learning for Domain Generalization (N19-2)

Copied to clipboard

Challenge: Using adversarial learning to train models on a higher level of abstraction to increase their robustness to lexical and stylistic variations is crucial for the integration of Semantic Parsing technologies in real applications.
Approach: They propose to perform Semantic Parsing with a domain classification adversarial task and an unsupervised domain discovery approach that yields equivalent improvements.
Outcome: The proposed approach improves on a French corpus of encyclopedic documents annotated with FrameNet and an unsupervised domain discovery approach yields equivalent improvements.
FrNewsLink : a corpus linking TV Broadcast News Segments and Press Articles (L18-1)

Copied to clipboard

Challenge: a corpus of TV Broadcast News resources is proposed to address several applicative tasks.
Approach: They propose to use a corpus to address several applicative tasks that are made public . they propose to gather TVBN shows and press articles and use them to study semantic similarity .
Outcome: The proposed corpus is based on 112 TVBN shows and press articles . it allows to study semantic similarity and multimedia News linking .
Statistical Deficiency for Task Inclusion Estimation (2025.acl-long)

Copied to clipboard

Challenge: Tasks are central in machine learning, as they are the most natural objects to assess the capabilities of current models.
Approach: They propose a theoretically grounded setup to define the notion of task and compute the inclusion between two tasks from a statistical deficiency point of view.
Outcome: The proposed model estimates the degree of inclusion between tasks on synthetic data and reconstructs the classic NLP pipeline.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations