Papers by Christophe Gravier

8 papers
T-REx: A Large Scale Alignment of Natural Language with Knowledge Base Triples (L18-1)

Copied to clipboard

Challenge: Existing datasets that provide alignments between natural language and knowledge bases (KB) triples are limited in size, lack coverage and are of unreported quality.
Approach: They propose to build a large scale dataset of alignments between Wikipedia abstracts and Wikidata triples that is two orders of magnitude larger than the largest available alignments dataset.
Outcome: The proposed dataset is two orders of magnitude larger than the largest available dataset and covers 2.5 times more predicates.
A Neural Few-Shot Text Classification Reality Check (2021.eacl-main)

Copied to clipboard

Challenge: Modern few-shot text classification models struggle when the amount of annotated data is scarce.
Approach: They compare neural few-shot classification models with NLP and computer vision models with transformers to test their performance.
Outcome: The proposed models perform almost equally on ARSC dataset, but not on the intent detection task.
HISTOIRESMORALES: A French Dataset for Assessing Moral Alignment (2025.naacl-long)

Copied to clipboard

Challenge: HistoiresMorales is a dataset based on moralStories in French . it is based upon annotations of moral values within the dataset .
Approach: They propose a dataset in French that aims to align language models with moral values . they use annotations to ensure their alignment with French norms .
Outcome: The proposed dataset guarantees grammatical accuracy and adaptation to the French cultural context.
PROTAUGMENT: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning (2021.acl-long)

Copied to clipboard

Challenge: Recent research considers few-shot intent detection as a meta-learning problem because of labeled data scarcity and the number of classes involved.
Approach: They propose a meta-learning algorithm for short texts classification that limits overfitting on the bias introduced by the few-shots classification objective at each episode.
Outcome: The proposed algorithm limits overfitting on the bias introduced by the few-shots classification objective at each episode.
Few-shot Pseudo-Labeling for Intent Detection (2020.coling-main)

Copied to clipboard

Challenge: Existing methods for labeling intents are expensive and time-consuming.
Approach: They propose a folding/unfolding hierarchical clustering algorithm which assigns weighted pseudo-labels to unlabeled user utterances.
Outcome: The proposed method performs better on multiple intent detection datasets and is stronger than existing methods.
Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types (N18-1)

Copied to clipboard

Challenge: Existing factoid question answering systems rely on annotated datasets such as SimpleQuestions to generate questions from knowledge graphs.
Approach: They propose a neural model that generates questions from knowledge graphs triples in a “zero-shot” setup.
Outcome: The proposed model outperforms state-of-the-art on this task.
Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata (N18-2)

Copied to clipboard

Challenge: Existing Wikipedia content is unevenly distributed among 287 languages . authors propose a neural network architecture that generates textual summaries from Wikidata triples .
Approach: They propose an automated approach to generate Wikipedia summaries from Wikidata triples using structured data.
Outcome: The proposed approach is tested on Arabic and Esperanto languages with limited editors and content in the most under-resourced Wikipedias.
Fair Text Classification with Wasserstein Independence (2023.emnlp-main)

Copied to clipboard

Challenge: a novel method for mitigating group fairness in text classification remains an open challenge . a recent paper focuses on the problem of group fair in the domain of natural language processing .
Approach: They propose a method for mitigating group fairness in neural text classification . they use adversarial training to induce Wasserstein independence between representations .
Outcome: The proposed method exhibits a comparable or better fairness-accuracy trade-off compared to existing methods.

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