Fast Vocabulary Transfer for Language Model Compression
Real-world business applications require a trade-off between language model performance and size. We propose a new method for model compression that relies on vocabulary transfer.
From Diverse Sources to a Unified Framework: Constructing an Operational Ontology for Fire Management
This article outlines the process and efforts undertaken to develop such an ontology, aiming to fill this gap.
An energy-based comparative analysis of common approaches to text classification in the Legal domain
In this work, we present a detailed quantitative comparison of LLM and traditional approaches (e.g. SVM) on the LexGLUE benchmark, which takes into account both performance (standard indices) and alternative metrics such as timing, power consumption and cost, in a word: the carbon-footprint.