Papers by Maximin Coavoux

12 papers
FlauBERT: Unsupervised Language Model Pre-training for French (2020.lrec-1)

Copied to clipboard

Challenge: Language models are a key step to achieve state-of-the-art results in many different Natural Language Processing (NLP) tasks.
Approach: They propose to use a language model that is pre-trained on a large and heterogeneous French corpus to train continuous word representations.
Outcome: The proposed model outperforms existing models on a large and heterogeneous French corpus.
Should Cross-Lingual AMR Parsing go Meta? An Empirical Assessment of Meta-Learning and Joint Learning AMR Parsing (2024.findings-emnlp)

Copied to clipboard

Challenge: Cross-lingual AMR parsing is a task of predicting AMR graphs in a target language when training data is available only in . et al. (2018) evaluated meta-learning for cross-lingual parse in Croatian, Farsi, Korean, Chinese, and French.
Approach: They propose to use meta-learning to tackle cross-lingual AMR parsing in a target language . they evaluate their models in k-shot scenarios and compare them to classical joint learning .
Outcome: The proposed model performs better in 0-shot evaluation for Croatian, Farsi, Korean, Chinese, and French.
Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech (2024.acl-short)

Copied to clipboard

Challenge: Direct dependency parsing of the speech signal is proposed as a way of incorporating prosodic information into the parser and bypassing the limitations of a pipeline approach.
Approach: They propose to use graph-based parsing and sequence labeling based parses to integrate prosodic information into the parser and bypass limitations of pipeline approaches.
Outcome: The proposed graph based approach outperforms a pipeline approach on a large treebank of spoken french, despite having 30% fewer parameters.
Limitations of Human Identification of Automatically Generated Text (2024.lrec-main)

Copied to clipboard

Challenge: Neural text generation tools such as ChatGPT are gaining popularity . human annotations are considered gold standard labels for multiple tasks .
Approach: They propose a new corpus in French and English for recognising automatically generated texts . they propose 'incontext' setup which makes explicit the interaction between two parties .
Outcome: The proposed model generates fluent text, which requires much closer reading than the current model.
Unsupervised Aspect-Based Multi-Document Abstractive Summarization (D19-54)

Copied to clipboard

Challenge: Existing methods for opinion summarization are expensive and do not deal with contradictory statements.
Approach: They propose an unsupervised abstractive summarization neural system that generates short summaries of reviews in a vector space.
Outcome: The proposed system can generate short summaries of user-generated reviews in a short paragraph, while nobody reads all reviews.
BERT-Proof Syntactic Structures: Investigating Errors in Discontinuous Constituency Parsing (2021.findings-acl)

Copied to clipboard

Challenge: Recent results show that pretrained language models can be used for many tasks with high accuracy and high performance.
Approach: They propose two methods for automatically analysing discontinuous parsers' errors.
Outcome: The proposed methods characterize errors of a state-of-the-art transition-based discontinuous parser and provide an overview of the contribution of BERT to this task.
Jargon: A Suite of Language Models and Evaluation Tasks for French Specialized Domains (2024.lrec-main)

Copied to clipboard

Challenge: Pretrained language models are the de facto backbone of most state-of-the-art NLP systems.
Approach: They propose a family of domain-specific pretrained PLMs for French focusing on three important domains: transcribed speech, medicine, and law.
Outcome: The proposed models perform better on transcribed speech, medicine, and law domains than state-of-the-art models on a diverse set of tasks and datasets.
BERT Is Not The Count: Learning to Match Mathematical Statements with Proofs (2023.eacl-main)

Copied to clipboard

Challenge: Existing work on mathematical article analysis uses natural language processing to solve complex mathematical articles.
Approach: They propose a bilinear similarity model and two decoding methods to match statements to proofs effectively.
Outcome: The proposed model matches proofs to statements without being aware of proofs, but it follows a relatively shallow symbolic analysis and matching to achieve that performance.
What Has LeBenchmark Learnt about French Syntax? (2024.lrec-main)

Copied to clipboard

Challenge: Pretrained acoustic models are increasingly used for downstream speech tasks such as automatic speech recognition, speech translation, spoken language understanding or speech parsing.
Approach: They propose to probing a pretrained acoustic model for French for syntactic information using the Orféo treebank.
Outcome: The proposed model is trained on 7k hours of spoken French and obtained reasonable results on tasks that require higher level linguistic knowledge.
Self-Supervised and Controlled Multi-Document Opinion Summarization (2021.eacl-main)

Copied to clipboard

Challenge: Existing unsupervised methods for summarizing reviews are based on bootstrapping and require a combination of loss functions or hierarchical latent variables to ensure that the generated summaries remain on-topic.
Approach: They propose a self-supervised setup that considers an individual document as a target summary for a set of similar documents.
Outcome: The proposed setup makes training simpler than previous approaches by relying only on standard log-likelihood loss and mainstream models.
Discontinuous Constituency Parsing with a Stack-Free Transition System and a Dynamic Oracle (N19-1)

Copied to clipboard

Challenge: Discontinuous constituency trees are derivations of Linear Context-Free Rewriting Systems (LCFRS), which makes them much harder to parse.
Approach: They propose a transition system that uses a set of parsing items with constant-time random access instead of storing subtrees in a stack .
Outcome: The proposed system constructs a discontinuous constituency tree in 4n–2 transitions for a sentence of length n.
Privacy-preserving Neural Representations of Text (D18-1)

Copied to clipboard

Challenge: a specific type of attack is used to characterize the privacy of neural representations for NLP tasks, in the context of privacy protection.
Approach: They propose several defense methods based on modified training objectives and characterize the tradeoff between privacy and the utility of neural representations.
Outcome: The proposed defenses improve the privacy of neural representations and characterize the tradeoff between privacy and utility of representations.

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