Transfer Learning for a Letter-Ngrams to Word Decoder in the Context of Historical Handwriting Recognition with Scarce Resources - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

Transfer Learning for a Letter-Ngrams to Word Decoder in the Context of Historical Handwriting Recognition with Scarce Resources

Abstract

Lack of data can be an issue when beginning a new study on historical handwritten documents. In order to deal with this, we present the character-based decoder part of a multilingual approach based on transductive transfer learning for a historical handwriting recognition task on Italian Comedy Registers. The decoder must build a sequence of characters that corresponds to a word from a vector of letter-ngrams. As learning data, we created a new dataset from untapped resources that covers the same domain and period of our Italian Comedy data, as well as resources from common domains, periods, or languages. We obtain a 97.42% Character Recognition Rate and a 86.57% Word Recognition Rate on our Italian Comedy data, despite a lexical coverage of 67% between the Italian Comedy data and the training data. These results show that an efficient system can be obtained by a carefully selecting the datasets used for the transfer learning.
Fichier principal
Vignette du fichier
COLING_2018.pdf (519.09 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01868743 , version 1 (05-09-2018)

Identifiers

  • HAL Id : hal-01868743 , version 1

Cite

Adeline Granet, Emmanuel Morin, Harold Mouchère, Solen Quiniou, Christian Viard-Gaudin. Transfer Learning for a Letter-Ngrams to Word Decoder in the Context of Historical Handwriting Recognition with Scarce Resources. 27th International Conference on Computational Linguistics (COLING), Aug 2018, Santa Fe, NM, United States. pp.1474-1484. ⟨hal-01868743⟩
240 View
189 Download

Share

Gmail Mastodon Facebook X LinkedIn More