Suchergebnisse - [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing

Unsupervised approach to text line extraction in Belfort civil registers of births

Autoren: Alkendi, Wissam Gechter, Franck Heyberger, Laurent et al.

Weitere Verfasser: Alkendi, Wissam Gechter, Franck Heyberger, Laurent et al.

Quelle: International Journal on Document Analysis and Recognition (IJDAR). 28:255-276

Schlagwörter: [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing, Unsupervised Approach, Handwritten Text Recognition, [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, Structured Data Representation, Text Line Extraction, Historical Documents, Belfort Civil Registers of Birth

Dateibeschreibung: application/pdf

Zugangs-URL: https://hal.science/hal-04846013v1
https://doi.org/10.1007/s10032-024-00507-5
https://hal.science/hal-04846013v1/document

Extracting circumstances of Covid-19 transmission from free text with large language models

Autoren: Bizel-Bizellot, Gaston Galmiche, Simon Lelandais, Benoît et al.

Weitere Verfasser: Bizel-Bizellot, Gaston Galmiche, Simon Lelandais, Benoît et al.

Quelle: Nat Commun

Schlagwörter: [SDV] Life Sciences [q-bio], [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], [SDV.SPEE] Life Sciences [q-bio]/Santé publique et épidémiologie, [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, Article

Dateibeschreibung: application/pdf

Zugangs-URL: https://pasteur.hal.science/pasteur-05172560v1/document
https://doi.org/10.1038/s41467-025-60762-w
https://pasteur.hal.science/pasteur-05172560v1

Phenotypes Extraction from Text: Analysis and Perspective in the LLM Era

Autoren: Baddour, Moussa Paquelet, Stéphane Rollier, Paul et al.

Weitere Verfasser: Baddour, Moussa Paquelet, Stéphane Rollier, Paul et al.

Quelle: 2024 IEEE 12th International Conference on Intelligent Systems (IS). :1-8

Schlagwörter: LLM, [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], phenotype, [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, phenoBERT, [INFO.INFO-IR] Computer Science [cs]/Information Retrieval [cs.IR], [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], genetic, entity linking, embeddings

Dateibeschreibung: application/pdf

Zugangs-URL: https://inria.hal.science/hal-04647016v1/document
https://inria.hal.science/hal-04647016v1
https://doi.org/10.1109/is61756.2024.10705235

MOSAIC: Multiple Observers Spotting AI Content

Autoren: Dubois, Matthieu Yvon, François Piantanida, Pablo

Weitere Verfasser: Dubois, Matthieu Yvon, François Piantanida, Pablo

Quelle: Findings of the Association for Computational Linguistics: ACL 2025. :24230-24247

Schlagwörter: Large Language Model, FOS: Computer and information sciences, Computer Science - Computation and Language, [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, Model Ensembling, Computation and Language (cs.CL), Artificial Text Detection

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2409.07615

Team INSAntive at SlavicNLP-2025 Shared Task: Data Augmentation and Enhancement via Explanations for Persuasion Technique Classification

Autoren: Wang, Yutong Nurbakova, Diana Calabretto, Sylvie

Weitere Verfasser: Wang, Yutong Nurbakova, Diana Calabretto, Sylvie

Quelle: Proceedings of the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025). :190-201

Schlagwörter: [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing

Dateibeschreibung: application/pdf

Zugangs-URL: https://hal.science/hal-05154028v1

Generating Explanations in Medical Question-Answering by Expectation Maximization Inference over Evidence

Autoren: Sun, Wei Li, Mingxiao Sileo, Damien et al.

Weitere Verfasser: Sun, Wei Li, Mingxiao Sileo, Damien et al.

Quelle: ACM Transactions on Computing for Healthcare. 6:1-23

Schlagwörter: [SDV.IB] Life Sciences [q-bio]/Bioengineering, FOS: Computer and information sciences, Technology, Science & Technology, Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Medical Question Answering, [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, Artificial Intelligence (cs.AI), [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], Computer Science, Computer Science, Interdisciplinary Applications, Life Sciences & Biomedicine, Explanation Generation, Computation and Language (cs.CL), Medical Informatics, Expectation Maximization

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2310.01299
https://hal.science/hal-05290617v1
https://hal.science/hal-05290617v1/document
https://doi.org/10.1145/3712296
https://lirias.kuleuven.be/handle/20.500.12942/772210
https://doi.org/10.1145/3712296

Federal Reserve Communication and the COVID‐19 Pandemic

Autoren: Benchimol, Jonathan Kazinnik, Sophia Saadon, Yossi

Weitere Verfasser: Benchimol, Jonathan Kazinnik, Sophia Saadon, Yossi

Quelle: The Manchester School. 93:464-484

Schlagwörter: FOS: Computer and information sciences, General Economics (econ.GN), Financial stability, Text mining, Economics, Information Theory, [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, Text analytics, Machine Learning (stat.ML), Financial crises, Data science, Machine leaning, Crisis, Machine Learning, FOS: Economics and business, E50, [SHS.STAT] Humanities and Social Sciences/Methods and statistics, Machine learning, Applications (stat.AP), E58, Computation and Language, [SHS.ECO] Humanities and Social Sciences/Economics and Finance, E52, C55, ddc:330, Information Theory (cs.IT), COVID-19, Text analysis, Unconventional monetary policy, General Economics, [STAT.ML] Statistics [stat]/Machine Learning [stat.ML], Central bank communication, C82, Applications, C81, E44, [PHYS.PHYS.PHYS-DATA-AN] Physics [physics]/Physics [physics]/Data Analysis, Statistics and Probability [physics.data-an], E63, Computation and Language (cs.CL)

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2508.04830
https://hdl.handle.net/10419/323832
https://hal.science/hal-05203069v1/document
https://doi.org/10.1111/manc.12520
https://hal.science/hal-05203069v1

CrisisTS: Coupling Social Media Textual Data and Meteorological Time Series for Urgency Classification

Autoren: Meunier, Romain Benamara, Farah Moriceau, Véronique et al.

Weitere Verfasser: Meunier, Romain Benamara, Farah Moriceau, Véronique et al.

Quelle: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). :16082-16099

Schlagwörter: [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing

Dateibeschreibung: application/pdf

DISPUTool 3.0: Fallacy Detection and Repairing in Argumentative Political Debates

Autoren: Goffredo, Pierpaolo Dore, Deborah Cabrio, Elena et al.

Weitere Verfasser: Goffredo, Pierpaolo Dore, Deborah Cabrio, Elena et al.

Quelle: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). :472-480

Schlagwörter: [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, [INFO.INFO-IR] Computer Science [cs]/Information Retrieval [cs.IR]

Dateibeschreibung: application/pdf

Zugangs-URL: https://hal.science/hal-05210504v1
https://hal.science/hal-05210504v1/document
https://doi.org/10.18653/v1/2025.acl-demo.45

Leveraging Graph Structural Knowledge to Improve Argument Relation Prediction in Political Debates

Autoren: Dore, Deborah Faralli, Stefano Villata, Serena et al.

Weitere Verfasser: Dore, Deborah Faralli, Stefano Villata, Serena et al.

Quelle: Proceedings of the 12th Argument mining Workshop. :74-86

Schlagwörter: [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, [INFO.INFO-IR] Computer Science [cs]/Information Retrieval [cs.IR]

Dateibeschreibung: application/pdf

MockConf: A Student Interpretation Dataset: Analysis, Word- and Span-level Alignment and Baselines

Autoren: Javorský, Dávid Bojar, Ondřej Yvon, François

Weitere Verfasser: Javorský, Dávid Bojar, Ondřej Yvon, François

Quelle: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). :16339-16356

Schlagwörter: FOS: Computer and information sciences, Automatic Interpreting, Computer Science - Computation and Language, [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, Computation and Language (cs.CL), Parallel Corpus Alignment, Corpus Analysis, Spoken Language Translation

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2506.04848

MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment

Autoren: Kargaran, Amir Hossein Modarressi, Ali Nikeghbal, Nafiseh et al.

Weitere Verfasser: Kargaran, Amir Hossein Modarressi, Ali Nikeghbal, Nafiseh et al.

Quelle: Findings of the Association for Computational Linguistics: ACL 2025. :27001-27023

Schlagwörter: FOS: Computer and information sciences, Natural Language Evaluation, Computer Science - Computation and Language, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Multilingual Language Models, [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, Computation and Language (cs.CL), Natural Language Processing

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2410.05873
https://hal.science/hal-05207048v1/document
https://hal.science/hal-05207048v1
https://doi.org/10.18653/v1/2025.findings-acl.1385

Understanding In-Context Machine Translation for Low-Resource Languages: A Case Study on Manchu

Autoren: Pei, Renhao Liu, Yihong Lin, Peiqin et al.

Weitere Verfasser: Pei, Renhao Liu, Yihong Lin, Peiqin et al.

Quelle: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). :8767-8788

Schlagwörter: Large Language Model, FOS: Computer and information sciences, Machine Translation, Computer Science - Computation and Language, Manchu Language, [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, In context learning, Computation and Language (cs.CL), Low-Resource Languages

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2502.11862
https://hal.science/hal-05188526v1

LlamATE: Automated terminology extraction using large‑scale generative language models

Autoren: Hanh, Tran Thi Hong González-Gallardo, Carlos-Emiliano Doucet, Antoine et al.

Weitere Verfasser: Hanh, Tran Thi Hong González-Gallardo, Carlos-Emiliano Doucet, Antoine et al.

Quelle: Terminology. International Journal of Theoretical and Applied Issues in Specialized Communication. 31:5-36

Schlagwörter: LLM, In-context learning, Prompt engineering, Self-verification, [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, Term extraction LLMs Prompt engineering In-context learning Llama-2-Chat Cross-domain Transfer learning Self-verification, LLMs, Cross-domain, Term extraction, Llama-2-Chat, Transfer learning

Dateibeschreibung: application/pdf

Overcoming Data Scarcity in Named Entity Recognition: Synthetic Data Generation with Large Language Models

Autoren: Dao, An Teranishi, Hiroki Matsumoto, Yuji et al.

Weitere Verfasser: Dao, An Teranishi, Hiroki Matsumoto, Yuji et al.

Quelle: Proceedings of the 24th Workshop on Biomedical Language Processing. :328-340

Schlagwörter: [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing

Prompting LLMs: Length Control for Isometric Machine Translation

Autoren: Javorský, Dávid Bojar, Ondřej Yvon, François et al.

Weitere Verfasser: Javorský, Dávid Bojar, Ondřej Yvon, François et al.

Quelle: Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025). :119-137

Schlagwörter: Isometric Machine Translation, FOS: Computer and information sciences, Computer Science - Computation and Language, [INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, Computation and Language (cs.CL), Multilingual Large Language Models, Spoken Language Translation

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2506.04855

How Programming Concepts and Neurons Are Shared in Code Language Models

Autoren: Kargaran, Amir Hossein Liu, Yihong Yvon, François et al.

Weitere Verfasser: Kargaran, Amir Hossein Liu, Yihong Yvon, François et al.

Quelle: Findings of the Association for Computational Linguistics: ACL 2025. :26905-26917

Schlagwörter: Software Engineering (cs.SE), FOS: Computer and information sciences, Computer Science - Software Engineering, Computer Science - Computation and Language, Computer Science - Programming Languages, [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, Computation and Language (cs.CL), Programming Languages (cs.PL)

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2506.01074

Is There Life on Mars? Studying the Context of Uncertainty in Astrobiology

Autoren: Atanassova, Iana Ningrum, Panggih Gutehrlé, Nicolas et al.

Weitere Verfasser: Atanassova, Iana Ningrum, Panggih Gutehrlé, Nicolas et al.

Quelle: International Conference on Scientometrics & Informetrics.

Schlagwörter: full text, LDA, [SHS.HISPHILSO] Humanities and Social Sciences/History, Philosophy and Sociology of Sciences, Uncertainty, astrobiology, [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, topic model, [SHS.LANGUE] Humanities and Social Sciences/Linguistics

Dateibeschreibung: application/pdf

Zugangs-URL: https://hal.science/hal-05129565v1

'Women do not have heart attacks!' Gender Biases in Automatically Generated Clinical Cases in French

Autoren: Ducel, Fanny Hiebel, Nicolas Ferret, Olivier et al.

Weitere Verfasser: Ducel, Fanny Hiebel, Nicolas Ferret, Olivier et al.

Quelle: Findings of the Association for Computational Linguistics: NAACL 2025. :7145-7159

Schlagwörter: LLM, Ethics, Clinical case, Bias, cas cliniques, genre, français, [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, modèle de langue, stéréotype, Stereotype, biais

Dateibeschreibung: application/pdf

Zugangs-URL: https://inria.hal.science/hal-05282965v1
https://inria.hal.science/hal-04938811v1
https://doi.org/10.18653/v1/2025.findings-naacl.398
https://inria.hal.science/hal-04938811v1/document

Ontology Enrichment with SWRL rules from text for greenhouse farming ; Enrichissement d'ontologie avec des règles SWRL à partir de texte pour la culture sous serre

Autoren: Armary, Pauline Spicher, Antoine El Vaigh, Cheikh Brahim et al.

Weitere Verfasser: Armary, Pauline Spicher, Antoine El Vaigh, Cheikh Brahim et al.

Quelle: 8ème édition de l’Atelier INtégration de sources/masses de données hétérogènes et Ontologies, dans le domaine des sciences du VIVant et de l’Environnement IN-OVIVE, adossé à la conférence Ingénierie des Connaissances @PFIA
https://hal.science/hal-05071439
8ème édition de l’Atelier INtégration de sources/masses de données hétérogènes et Ontologies, dans le domaine des sciences du VIVant et de l’Environnement IN-OVIVE, adossé à la conférence Ingénierie des Connaissances @PFIA, AFIA- Association Française d’Intelligence Artificielle, Jul 2025, Dijon (Bourgogne), France

Schlagwörter: Greenhouse, ontology, ontology enrichment, SWRL, Ontology Learning, Construction automatique d'ontologie, ontologie, Serre, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing, [SDE]Environmental Sciences

Geographisches Schlagwort: Dijon (Bourgogne), France

Verfügbarkeit: https://hal.science/hal-05071439
https://hal.science/hal-05071439v1/document
https://hal.science/hal-05071439v1/file/Armary_et_al-InOvive_Enrichissement_Ontologie_SWRL_serre_final_2025_05_15.pdf