activity
20182026
most citedLearning to Match Mathematical Statements with Proofs

2 citations · 5 across the 8 of their papers we have counts for

collaborators
Showing cs.CLShow all

14 papers · 1 filter

cs.CL2026

Pantagruel: Unified Self-Supervised Encoders for French Text and Speech

Phuong-Hang Le, Valentin Pelloin, Arnault Chatelain +27

We release Pantagruel models, a new family of self-supervised encoder models for French text and speech. Instead of predicting modality-tailored targets such as textual tokens or s…

cs.CL2025

ding-01 :ARG0: An AMR Corpus for Spontaneous French Dialogue

Jeongwoo Kang, Maria Boritchev, Maximin Coavoux

We present our work to build a French semantic corpus by annotating French dialogue in Abstract Meaning Representation (AMR). Specifically, we annotate the DinG corpus, consisting…

cs.CL2025

Reassessing Graph Linearization for Sequence-to-sequence AMR Parsing: On the Advantages and Limitations of Triple-Based Encoding

Jeongwoo Kang, Maximin Coavoux, Cédric Lopez +1

Sequence-to-sequence models are widely used to train Abstract Meaning Representation (Banarescu et al., 2013, AMR) parsers. To train such models, AMR graphs have to be linearized i…

cs.CL2024

Should Cross-Lingual AMR Parsing go Meta? An Empirical Assessment of Meta-Learning and Joint Learning AMR Parsing

Jeongwoo Kang, Maximin Coavoux, Cédric Lopez +1

Cross-lingual AMR parsing is the task of predicting AMR graphs in a target language when training data is available only in a source language. Due to the small size of AMR training…

cs.CL2024

Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech

Adrien Pupier, Maximin Coavoux, Jérôme Goulian +1

Direct dependency parsing of the speech signal -- as opposed to parsing speech transcriptions -- has recently been proposed as a task (Pupier et al. 2022), as a way of incorporatin…

cs.CL2024

What has LeBenchmark Learnt about French Syntax?

Zdravko Dugonjić, Adrien Pupier, Benjamin Lecouteux +1

The paper reports on a series of experiments aiming at probing LeBenchmark, a pretrained acoustic model trained on 7k hours of spoken French, for syntactic information. Pretrained…