Related papers: Algorithmes de classification et d'optimisation: p…

The 2013 D\'efi de Fouille de Textes (DEFT) campaign is interested in two types of language analysis tasks, the document classification and the information extraction in the specialized domain of cuisine recipes. We present the systems that…

Fine-tuning large language models (LLMs) is essential for enhancing their performance on specific tasks but is often resource-intensive due to redundant or uninformative data. To address this inefficiency, we introduce DELIFT (Data…

Recent advances have led to the availability of many pre-trained language models (PLMs); however, a question that remains is how much data is truly needed to fine-tune PLMs for downstream tasks? In this work, we introduce DEFT-UCS, a…

This paper constitutes an extension to the report on DISA-MU team participation in the ImageCLEF 2014 Scalable Concept Image Annotation Task as published in [3]. Specifically, we introduce a new similarity search component that was…

This paper reports on Qwant Research contribution to tasks 2 and 3 of the DEFT 2019's challenge, focusing on French clinical cases analysis. Task 2 is a task on semantic similarity between clinical cases and discussions. For this task, we…

Efficient fine-tuning of pre-trained Text-to-Image (T2I) models involves adjusting the model to suit a particular task or dataset while minimizing computational resources and limiting the number of trainable parameters. However, it often…

Modern IC complexity drives test pattern growth, with the majority of patterns targeting a small set of hard-to-detect (HTD) faults. This motivates new ATPG algorithms to improve test effectiveness specifically for HTD faults. This paper…

This companion paper complements the main DEFT'10 article describing the MARF approach (arXiv:0905.1235) to the DEFT'10 NLP challenge (described at http://www.groupes.polymtl.ca/taln2010/deft.php in French). This paper is aimed to present…

Large Language Models (LLMs) often do not perform well on queries that require the aggregation of information across texts. To better evaluate this setting and facilitate modeling efforts, we introduce TACT - Text And Calculations through…

Generative modelling paradigms based on denoising diffusion processes have emerged as a leading candidate for conditional sampling in inverse problems. In many real-world applications, we often have access to large, expensively trained…

We present work on deception detection, where, given a spoken claim, we aim to predict its factuality. While previous work in the speech community has relied on recordings from staged setups where people were asked to tell the truth or to…

One of us (MEC) developed a hands-on workbook for density-functional theory (DFT) during the summer of 2020. The idea was to have something that could be used to provide practical teaching for students at the Masters or advanced…

This report describes the methods employed by the Democritus University of Thrace (DUTH) team for participating in SemEval-2020 Task 11: Detection of Propaganda Techniques in News Articles. Our team dealt with Subtask 2: Technique…

This paper describes the Duluth systems that participated in Task 14 of SemEval 2016, Semantic Taxonomy Enrichment. There were three related systems in the formal evaluation which are discussed here, along with numerous post--evaluation…

Information Extraction from scientific literature can be challenging due to the highly specialised nature of such text. We describe our entity recognition methods developed as part of the DEAL (Detecting Entities in the Astrophysics…

We present the shared task on Fine-Grained Propaganda Detection, which was organized as part of the NLP4IF workshop at EMNLP-IJCNLP 2019. There were two subtasks. FLC is a fragment-level task that asks for the identification of propagandist…

Disentanglement is a highly desirable property of representation owing to its similarity to human understanding and reasoning. Many works achieve disentanglement upon information bottlenecks (IB). Despite their elegant mathematical…

Large pre-trained language models have shown promise for few-shot learning, completing text-based tasks given only a few task-specific examples. Will models soon solve classification tasks that have so far been reserved for human research…

This paper describes the Duluth systems that participated in SemEval--2020 Task 12, Multilingual Offensive Language Identification in Social Media (OffensEval--2020). We participated in the three English language tasks. Our systems provide…

Scaling data and model size has been proven effective for boosting the performance of large language models. In addition to training-time scaling, recent studies have revealed that increasing test-time computational resources can further…