- From: Christophe Roche <roche.university@gmail.com>
- Date: Tue, 14 May 2024 09:49:24 +0300
- To: semantic-web@w3.org
- Message-ID: <47ab2b83-3c8e-40b7-8b7a-6b43b88627b2@gmail.com>
[Apologies for multiple postings] *=============================================* *TOTh 2024: **Terminology & Ontology: Theories and applications* *University Savoie Mont Blanc (France)* *Last Call for Registration - Training & Conference* _Conference_: 6-7 June 2024, http://toth.condillac.org/ _Training_: 4-5 June 2024, http://toth.condillac.org/training *=============================================* *Opening Talk: **"An overview of automatic term extraction"* http://toth.condillac.org/opening-talk "Automatic term extraction (ATE) is a natural language processing (NLP) task is meant to ease the effort of manually identifying terms from domain-specific corpora by providing a list of candidate terms. As units of knowledge in a specific field of expertise, extracted terms are not only beneficial for several terminographical tasks, but also support and improve several complex downstream tasks, e.g., information retrieval, machine translation, topic detection, and sentiment analysis. ATE systems, along with annotated datasets, have been studied and developed widely for decades, but recently we observed a surge in novel neural systems to address this task. The talk will present an overview of recent ATE approaches, notably deep learning-based approaches, with a focus on Transformer-based neural models. We will also compare them to the previous ATE approaches, which were mainly based on feature engineering and non-neural supervised learning algorithms." Prof Antoine Doucet, Université de la Rochelle (France) *=============================================* Prof Christophe Roche University of Crete (Greece) - ERA Chair Holder University Savoie Mont Blanc (France) - Emeritus https://talos-ai4ssh.uoc.gr/ http://christophe-roche.fr/ roche.university@gmail.com
Received on Tuesday, 14 May 2024 11:24:12 UTC