9 papers
Can We Do Interpretable NLI with Graphs Based on Atomic Propositions?
Younes Boufouss, Luc Pommeret, Thomas Gerald +2
While Large Language Model (LLM)-based Natural Language Inference (NLI) systems achieve high accuracy, their decision-making processes lack auditable structures. This paper explore…
LLM-based Atomic Propositions help weak extractors: Evaluation of a Propositioner for triplet extraction
Luc Pommeret, Thomas Gerald, Patrick Paroubek +3
Knowledge Graph construction from natural language requires extracting structured triplets from complex, information-dense sentences. In this paper, we investigate if the decomposi…
Leveraging Information Retrieval to Enhance Spoken Language Understanding Prompts in Few-Shot Learning
Pierre Lepagnol, Sahar Ghannay, Thomas Gerald +2
Understanding user queries is fundamental in many applications, such as home assistants, booking systems, or recommendations. Accordingly, it is crucial to develop accurate Spoken…
Small Language Models are Good Too: An Empirical Study of Zero-Shot Classification
Pierre Lepagnol, Thomas Gerald, Sahar Ghannay +2
This study is part of the debate on the efficiency of large versus small language models for text classification by prompting.We assess the performance of small language models in…
New Semantic Task for the French Spoken Language Understanding MEDIA Benchmark
Nadège Alavoine, Gaëlle Laperriere, Christophe Servan +2
Intent classification and slot-filling are essential tasks of Spoken Language Understanding (SLU). In most SLUsystems, those tasks are realized by independent modules. For about fi…
mALBERT: Is a Compact Multilingual BERT Model Still Worth It?
Christophe Servan, Sahar Ghannay, Sophie Rosset
Within the current trend of Pretained Language Models (PLM), emerge more and more criticisms about the ethical andecological impact of such models. In this article, considering the…
Benchmarking Transformers-based models on French Spoken Language Understanding tasks
Oralie Cattan, Sahar Ghannay, Christophe Servan +1
In the last five years, the rise of the self-attentional Transformer-based architectures led to state-of-the-art performances over many natural language tasks. Although these appro…
On the Usability of Transformers-based models for a French Question-Answering task
Oralie Cattan, Christophe Servan, Sophie Rosset
For many tasks, state-of-the-art results have been achieved with Transformer-based architectures, resulting in a paradigmatic shift in practices from the use of task-specific archi…
Overlap-aware low-latency online speaker diarization based on end-to-end local segmentation
Juan M. Coria, Hervé Bredin, Sahar Ghannay +1
We propose to address online speaker diarization as a combination of incremental clustering and local diarization applied to a rolling buffer updated every 500ms. Every single step…