Papers by Benoit Crabbé

13 papers
FrSemCor: Annotating a French Corpus with Supersenses (2020.lrec-1)

Copied to clipboard

Challenge: a new project aims to provide a sense-annotated corpus of French for NLP and linguistics research . the project uses WordNet Unique Beginners as semantic tags to provide interoperability .
Approach: They propose to use WordNet Unique Beginners as semantic tags to annotate French nouns . the project aims to provide a gold standard resource for linguistics and linguistic research .
Outcome: The proposed resource is released online under a Creative Commons license.
The impact of lexical and grammatical processing on generating code from natural language (2022.findings-acl)

Copied to clipboard

Challenge: Yin and Neubig (2018) identify four key components of importance for natural language to code translation.
Approach: They propose a seq2seq-based architecture that relies on a grammar-based decoder and a lexical substitution component for natural language to code translation.
Outcome: The proposed architecture relies on a grammar-based decoder and a BERT encoder . the proposed architecture is based on lexical substitutions in natural language to code translation .
On the Relation Between Fine-Tuning, Topological Properties, and Task Performance in Sense-Enhanced Embeddings (2025.acl-long)

Copied to clipboard

Challenge: Enhanced word embeddings do not align well with word senses, resulting in poor performance on word sense identification tasks.
Approach: They propose to use two methods to fine-tune embeddings to identify the topological properties that contribute to sense-enhanced embeddables.
Outcome: The proposed methods improve the embeddings’ ability to capture nuanced semantic distinctions while reducing their expressiveness.
Contrasting distinct structured views to learn sentence embeddings (2021.eacl-srw)

Copied to clipboard

Challenge: Existing methods to build sentence embeddings rely on a similar Recurrent Neural Network (RNN) heterogeneity of performances across models and tasks makes us assume some structures might be better adapted given the considered task or sentence.
Approach: They propose a self-supervised method that builds sentence embeddings from syntactic structures . they hypothesize that some linguistic representations might be better adapted given the task .
Outcome: The proposed method outperforms comparable methods on several tasks from standard sentence embedding benchmarks.
NuNER: Entity Recognition Encoder Pre-training via LLM-Annotated Data (2024.emnlp-main)

Copied to clipboard

Challenge: Named Entity Recognition (NER) is a core component of natural language processing, present in a variety of applications such as medical coding, financial news analysis, or legal documents parsing.
Approach: They propose to use Large Language Models (LLMs) to create NuNER, a compact language representation model specialized in the Named Entity Recognition task.
Outcome: The proposed model outperforms similar-sized foundation models in the few-shot regime and is based on a human-annotated dataset.
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.
Unifying Parsing and Tree-Structured Models for Generating Sentence Semantic Representations (2022.naacl-srw)

Copied to clipboard

Challenge: Existing tree-based models require handannotated data to be trained.
Approach: They propose a tree-based model that learns its composition function together with its structure.
Outcome: The proposed model outperforms existing models on downstream tasks and is competitive with Bert base model.
CodeInsight: A Curated Dataset of Practical Coding Solutions from Stack Overflow (2024.findings-acl)

Copied to clipboard

Challenge: Comprising 3,402 crafted examples, our dataset is designed for both model finetuning and standalone evaluation.
Approach: They propose a dataset that provides examples that include a clarified intent, code snippets associated, and an average of three related unit tests.
Outcome: The proposed dataset includes 3,402 hand-written examples and 3,121 unrefined examples.
BERTrade: Using Contextual Embeddings to Parse Old French (2022.lrec-1)

Copied to clipboard

Challenge: a growing interest in digital humanities for automatic processing and annotation of historical texts is generating new models for historical languages.
Approach: They use POS-tagging and dependency parsing to evaluate contextual word embedding models . Old French is one of the historical languages for which they have the largest amount of syntactically annotated data .
Outcome: The proposed model can be used to improve performance in Old French, the authors show . they use POS-tagging and dependency parsing to evaluate the model's quality .
Are Transformers a Modern Version of ELIZA? Observations on French Object Verb Agreement (2021.emnlp-main)

Copied to clipboard

Challenge: Recent studies have shown that unsupervised sentence representations of neural networks encode syntactic information by observing that neural language models are able to predict the agreement between a verb and its subject.
Approach: They propose to take an alternative look at these results by studying whether neural networks are able to build an abstract sentence representation rather than capture surface statistical regularities.
Outcome: The proposed model can achieve high accuracy on the long-range French object-verb agreement, indicating a possible flaw in the model's syntactic ability.
Variable beam search for generative neural parsing and its relevance for the analysis of neuro-imaging signal (D19-1)

Copied to clipboard

Challenge: a variable beam size inference method is proposed for generative parsing for RNNG . the proposed method is not sensitive to lexical biases faced by standard beam search .
Approach: They propose a method of variable beam size inference for Recurrent Neural Network Grammar by drawing inspiration from sequential Monte-Carlo methods such as particle filtering.
Outcome: The proposed method is based on a generative parsing framework that can be used to model brain activity during online sentence comprehension.
How Many Layers and Why? An Analysis of the Model Depth in Transformers (2021.acl-srw)

Copied to clipboard

Challenge: In deep transformers, weights are tied across layers, resulting in multiple layers.
Approach: They propose a variant of Albert that adapts the number of layers for each token of the input.
Outcome: The proposed model implements the key specificity of Albert and iterates on token representations over time.
How Distributed are Distributed Representations? An Observation on the Locality of Syntactic Information in Verb Agreement Tasks (2022.acl-short)

Copied to clipboard

Challenge: Using probing, causal analysis and feature selection, we find that syntactic information is encoded locally in the transformers representations consistent with the French grammar.
Approach: They address the question of the localization of syntactic information encoded in transformers representations by probing, causal analysis and feature selection methods.
Outcome: The proposed representations are consistent with the object-past participle agreement in French and are consistent in both languages.

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