Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 5
ǂA ǂsurvey on bipartite graphs embedding
Edward Giamphy, Jean‑Loup Guillaume, Antoine Doucet, Kevin Sanchis
Izvirni znanstveni članek
Oznake: vgrajevanje grafov;dvodelni graf;učenje reprezentacij;predstavitve vzorcev na osnovi grafov;strojno učenje;rudarjenje podatkov;anketa;primerjalna analiza;graph embeddings;bipartite graph;representation learning;graph-based pattern representations;machine learning;data mining;survey;benchmark;
Research on graph representation learning (a.k.a. embedding) has received great attention in recent years and shows effective results for various types of networks. Nevertheless, few initiatives have been focused on the particular case of embeddings for bipartite graphs. In this paper, we first defi ...
Leto: 2023 Vir: Fakulteta za računalništvo in informatiko (UL FRI)
Evaluating robustness of LLMs in question answering on multilingual noisy OCR data
Bhawna Piryani, Jamshid Mozafari, Abdelrahman Abdallah, Antoine Doucet, Adam Jatowt
Objavljeni znanstveni prispevek na konferenci
Oznake: večjezično zagotavljanje kakovosti;optično prepoznavanje besedila;veliki jezikovni modeli;multilingual QA;OCR text;large language models;
Optical Character Recognition (OCR) plays a crucial role in digitizing historical and multilingual documents, yet OCR errors - imperfect extraction of text, including character insertion, deletion, and substitution can significantly impact downstream tasks like question-answering (QA). In this work, ...
Leto: 2025 Vir: Fakulteta za računalništvo in informatiko (UL FRI)
Terminology extraction and alignment for the translation industry
Andraž Repar, Senja Pollak, Marko Robnik Šikonja, Špela Vintar, Antoine Doucet
Doktorska disertacija
Oznake: termini;luščenje;poravnava terminologije;prevajalska industrija;korpusi;terminology extraction;translation industry;corpus;
Terminology extraction and alignment for the translation industry
Leto: 2025 Vir: Repozitorij samostojnih visokošolskih in višješolskih izobraževalnih organizacij
Neural approaches to automatic terminology extraction
Hanh Thi Hong Tran, Senja Pollak, Antoine Doucet, Marko Robnik Šikonja
Doktorska disertacija
Oznake: automatic terminology extraction;transformers;token classification;natural language processing;doctoral dissertations;
Leto: 2024 Vir: Repozitorij samostojnih visokošolskih in višješolskih izobraževalnih organizacij
Recent advances in automatic term extraction
Hanh Thi Hong Tran, Matej Martinc, Jaya Caporusso, Julien Delaunay, Antoine Doucet, Senja Pollak
Izvirni znanstveni članek
Oznake: računalniške metodologije;obdelava naravnega jezika;nevronske mreže;jezikovni viri;jezikovni modeli;transformatorji;avtomatsko pridobivanje izrazov;ATE;jeziki z malo viri;enojezični;večjezični;globoko učenje;učenje z ničelnim številom poskusov;učenje z malo poskusi;prenosno učenje;hitro inženirstvo;jezikovni modeli velikega obsega;computing methodologies;natural language processing;neural networks;language resources;language models;transformers;automatic term extraction;low-resourced languages;monolingual;multilingual;deep learning;zero-shot;few-shot;transfer learning;prompt engineering;large-scale language models;LLMs;
Automatic terminology or term extraction (ATE) is a Natural Language Processing (NLP) task intended to automatically identify specialized terms present in domain-specific corpora. As units of knowledge in a speciic ield of expertise, extracted terms are not only beneicial for several terminographica ...
Leto: 2026 Vir: Fakulteta za računalništvo in informatiko (UL FRI)
Št. zadetkov: 5
Ključne besede:
Leto izdaje:
Avtorji:
Repozitorij:
Tipologija:
Jezik: