A
Ahmed Hamdi
Researcher at University of La Rochelle
Publications - 20
Citations - 250
Ahmed Hamdi is an academic researcher from University of La Rochelle. The author has contributed to research in topics: Named-entity recognition & Computer science. The author has an hindex of 8, co-authored 20 publications receiving 128 citations.
Papers
More filters
Proceedings ArticleDOI
An analysis of the performance of named entity recognition over ocred documents
TL;DR: Estimating the performance of NER systems through OCRed data exhaustively iscusses NER errors arising from OCR errors, the correlation between NER accuracy and OCR error rates is studied, and the cost of character insertion, deletion and substitution in named entities is estimated.
Proceedings ArticleDOI
Alleviating Digitization Errors in Named Entity Recognition for Historical Documents
Emanuela Boros,Ahmed Hamdi,Elvys Linhares Pontes,Luis Adrián Cabrera-Diego,Jose G. Moreno,Nicolas Sidere,Antoine Doucet +6 more
TL;DR: This paper proposes a model based on a hierarchical stack of Transformers to approach the NER task for historical data, and shows that the proposed model clearly improves the results on both historical datasets, and does not degrade the results for modern datasets.
Proceedings ArticleDOI
A Multilingual Dataset for Named Entity Recognition, Entity Linking and Stance Detection in Historical Newspapers
Ahmed Hamdi,Elvys Linhares Pontes,Emanuela Boros,Thi Tuyet Hai Nguyen,Günter Hackl,Jose G. Moreno,Antoine Doucet +6 more
TL;DR: The NewsEye dataset as discussed by the authors is a multilingual dataset for named entity recognition and linking enriched with stances towards named entities, which consists of diachronic historical newspaper material published between 1850 and 1950 in French, German, Finnish, and Swedish.
Book ChapterDOI
Impact of OCR Quality on Named Entity Linking
TL;DR: This paper aims to evaluate the performance of named entity linking over digitized documents with different levels of OCR quality, and provides the first evaluation benchmark for NEL over degraded documents.
The Effects of Factorizing Root and Pattern Mapping in Bidirectional Tunisian - Standard Arabic Machine Translation
TL;DR: An architecture for a translation of the dialect into Modern Standard Arabic into Tunisian Arabic verbs is described and an evaluation demonstrates that the use of a decent coverage root+pattern lexicon of Tunisian and MSA with a backoff that assumes independence of mapping roots and patterns is optimal in reducing overall ambiguity and increasing recall.