| 1 |
Obvie: interface web pour la fouille et la comparaison de textes
|
|
|
|
In: Atelier DigitAl Humanities and cuLtural herItAge: data and knowledge management and analysis durant la conférence francophone sur l'Extraction et la Gestion des Connaissances (egc2022) ; https://hal.archives-ouvertes.fr/hal-03543362 ; Atelier DigitAl Humanities and cuLtural herItAge: data and knowledge management and analysis durant la conférence francophone sur l'Extraction et la Gestion des Connaissances (egc2022), Jan 2022, Blois, France ; https://egc2022.univ-tours.fr/ateliers/ (2022)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Corpus-based Language Universals Analysis using Universal Dependencies ; Analyse orientée corpus d'universaux linguistiques sur Universal Dependencies
|
|
|
|
In: SyntaxFest Quasy 2021 - Quantitative Syntax ; https://hal.inria.fr/hal-03501774 ; SyntaxFest Quasy 2021 - Quantitative Syntax, Mar 2022, Sofia, Bulgaria (2022)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Corpus-based Language Universals Analysis using Universal Dependencies ; Analyse orientée corpus d'universaux linguistiques sur Universal Dependencies
|
|
|
|
In: Quasy (Quantitative Syntax), SyntaxFest 2021 ; https://hal.inria.fr/hal-03501774 ; Quasy (Quantitative Syntax), SyntaxFest 2021, Mar 2022, Sofia, Bulgaria (2022)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Assessing the impact of OCR noise on multilingual event detection over digitised documents
|
|
|
|
In: ISSN: 1432-5012 ; EISSN: 1432-1300 ; International Journal on Digital Libraries ; https://hal.archives-ouvertes.fr/hal-03635985 ; International Journal on Digital Libraries, Springer Verlag, 2022, ⟨10.1007/s00799-022-00325-2⟩ (2022)
|
|
Abstract:
International audience ; Event detection (ED) is a crucial task for natural language processing (NLP) and it involves the identification of instances of specified types of events in text and their classification into event types. The detection of events from digitised documents could enable historians to gather and combine a large amount of information into an integrated whole, a panoramic interpretation of the past. However, the level of degradation of digitised documents and the quality of the optical character recognition (OCR) tools might hinder the performance of an event detection system. While several studies have been performed in detecting events from historical documents, the transcribed documents needed to be hand-validated which implied a great effort of human expertise and manual labor-intensive work. Thus, in this study, we explore the robustness of two different event detection language-independent models to OCR noise, over two datasets that cover different event types and multiple languages. We aim at analysing their ability to mitigate problems caused by the low quality of the digitised documents and we simulate the existence of transcribed data, synthesised from clean annotated text, by injecting synthetic noise. For creating the noisy synthetic data, we chose to utilise four main types of noise that commonly occur after the digitisation process: Character Degradation, Bleed Through, Blur, and Phantom Character. Finally, we conclude that the imbalance of the datasets, the richness of the different annotation styles, and the language characteristics are the most important factors that can influence event detection in digitised documents.
|
|
Keyword:
[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC]; [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR]; [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]; [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing; Digitised Documents; Event Detection; Information Extraction
|
|
URL: https://hal.archives-ouvertes.fr/hal-03635985/file/IJDL2022-Assessing%20the%20Impact%20of%20OCR%20Noise%20on%20Multilingual%20Event%20Detection%20over%20Digitised%20Documents.pdf
https://doi.org/10.1007/s00799-022-00325-2
https://hal.archives-ouvertes.fr/hal-03635985/document
https://hal.archives-ouvertes.fr/hal-03635985
|
|
BASE
|
|
Hide details
|
|
|
| 5 |
French CrowS-Pairs: Extending a challenge dataset for measuring social bias in masked language models to a language other than English
|
|
|
|
In: ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics ; https://hal.inria.fr/hal-03629677 ; ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, May 2022, Dublin, Ireland (2022)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?
|
|
|
|
In: Seventh Workshop on Noisy User-generated Text (W-NUT 2021, colocated with EMNLP 2021) ; https://hal.inria.fr/hal-03527328 ; Seventh Workshop on Noisy User-generated Text (W-NUT 2021, colocated with EMNLP 2021), Jan 2022, punta cana, Dominican Republic ; https://aclanthology.org/2021.wnut-1.47/ (2022)
|
|
BASE
|
|
Show details
|
|
|
|
|
