{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T20:20:58Z","timestamp":1760473258833,"version":"3.41.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031705519"},{"type":"electronic","value":"9783031705526"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-70552-6_10","type":"book-chapter","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:02:14Z","timestamp":1725940934000},"page":"167-182","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Revisiting N-Gram Models: Their Impact in\u00a0Modern Neural Networks for\u00a0Handwritten Text Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6174-9865","authenticated-orcid":false,"given":"Sol\u00e8ne","family":"Tarride","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7508-4080","authenticated-orcid":false,"given":"Christopher","family":"Kermorvant","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"10_CR1","doi-asserted-by":"publisher","unstructured":"Arora, A., et al.: Using ASR methods for OCR. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 663\u2013668 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00111","DOI":"10.1109\/ICDAR.2019.00111"},{"key":"10_CR2","doi-asserted-by":"publisher","unstructured":"Beyer, Y., Solberg, P.E.: Norhand v2\/dataset for handwritten text recognition in Norwegian [data set] (2024). https:\/\/doi.org\/10.5281\/zenodo.10555698","DOI":"10.5281\/zenodo.10555698"},{"key":"10_CR3","unstructured":"Blecher, L., Cucurull, G., Scialom, T., Stojnic, R.: Nougat: Neural Optical Understanding for Academic Documents (2023). https:\/\/arxiv.org\/abs\/2308.13418"},{"key":"10_CR4","doi-asserted-by":"publisher","unstructured":"Bluche, T.: Joint line segmentation and transcription for end-to-end handwritten paragraph recognition. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS 2016, pp. 838\u2013846. Curran Associates Inc., Red Hook (2016). https:\/\/doi.org\/10.5555\/3157096.3157190","DOI":"10.5555\/3157096.3157190"},{"key":"10_CR5","doi-asserted-by":"publisher","unstructured":"Bluche, T., Louradour, J., Knibbe, M., Moysset, B., Benzeghiba, M.F., Kermorvant, C.: The A2iA handwritten arabic text recognition system at the OpenHaRT2013 evaluation campaign. In: Document Analysis Systems (2014). https:\/\/doi.org\/10.1109\/DAS.2014.40","DOI":"10.1109\/DAS.2014.40"},{"issue":"4","key":"10_CR6","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1006\/csla.1999.0128","volume":"13","author":"SF Chen","year":"1999","unstructured":"Chen, S.F., Goodman, J.: An empirical study of smoothing techniques for language modeling. Comput. Speech Lang. 13(4), 359\u2013394 (1999). https:\/\/doi.org\/10.1006\/csla.1999.0128","journal-title":"Comput. Speech Lang."},{"key":"10_CR7","doi-asserted-by":"publisher","unstructured":"Choi, H., Lee, J., Yang, J.: N-gram in swin transformers for efficient lightweight image super-resolution. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2071\u20132081. IEEE Computer Society, Los Alamitos (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00206","DOI":"10.1109\/CVPR52729.2023.00206"},{"key":"10_CR8","doi-asserted-by":"publisher","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: DAN: a segmentation-free document attention network for handwritten document recognition. IEEE Trans. Pattern Anal. Mach. Intell. 1\u201317 (2023). https:\/\/doi.org\/10.1109\/tpami.2023.3235826","DOI":"10.1109\/tpami.2023.3235826"},{"issue":"1","key":"10_CR9","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1109\/TPAMI.2022.3144899","volume":"45","author":"D Coquenet","year":"2023","unstructured":"Coquenet, D., Chatelain, C., Paquet, T.: End-to-end handwritten paragraph text recognition using a vertical attention network. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 508\u2013524 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2022.3144899","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10_CR10","unstructured":"Diaz, D.H., Qin, S., Ingle, R.R., Fujii, Y., Bissacco, A.: Rethinking text line recognition models. CoRR abs\/2104.07787 (2021)"},{"key":"10_CR11","doi-asserted-by":"publisher","unstructured":"Grosicki, E., El-Abed, H.: ICDAR 2011 - French handwriting recognition competition. In: 2011 International Conference on Document Analysis and Recognition, pp. 1459\u20131463 (2011). https:\/\/doi.org\/10.1109\/ICDAR.2011.290","DOI":"10.1109\/ICDAR.2011.290"},{"key":"10_CR12","unstructured":"Jurafsky, D., Martin, J.: Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition (2020). https:\/\/web.stanford.edu\/~jurafsky\/slp3\/ed3book.pdf"},{"key":"10_CR13","doi-asserted-by":"publisher","unstructured":"Kozielski, M., Doetsch, P., Ney, H.: Improvements in RWTH\u2019s system for off-line handwriting recognition. In: International Conference on Document Analysis and Recognition (2013). https:\/\/doi.org\/10.1109\/ICDAR.2013.190","DOI":"10.1109\/ICDAR.2013.190"},{"key":"10_CR14","doi-asserted-by":"publisher","unstructured":"Kudo, T.: Subword regularization: Improving neural network translation models with multiple subword candidates. In: Gurevych, I., Miyao, Y. (eds.) Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Melbourne, Australia, pp. 66\u201375. Association for Computational Linguistics (2018). https:\/\/doi.org\/10.18653\/v1\/P18-1007","DOI":"10.18653\/v1\/P18-1007"},{"key":"10_CR15","doi-asserted-by":"publisher","unstructured":"Kudo, T., Richardson, J.: Sentencepiece: a simple and language independent subword tokenizer and detokenizer for neural text processing. CoRR abs\/1808.06226 (2018). https:\/\/doi.org\/10.18653\/v1\/D18-2012","DOI":"10.18653\/v1\/D18-2012"},{"key":"10_CR16","doi-asserted-by":"publisher","unstructured":"Kumar, S., Nirschl, M., Holtmann-Rice, D., Liao, H., Suresh, A.T., Yu, F.: Lattice rescoring strategies for long short term memory language models in speech recognition (2017). https:\/\/doi.org\/10.1109\/ASRU.2017.8268931","DOI":"10.1109\/ASRU.2017.8268931"},{"key":"10_CR17","doi-asserted-by":"publisher","unstructured":"Li, M., et al.: TrOCR: transformer-based optical character recognition with pre-trained models. In: AAAI Conference on Artificial Intelligence (2021). https:\/\/doi.org\/10.1609\/aaai.v37i11.26538","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"10_CR18","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1007\/978-3-031-06555-2_27","volume-title":"DAS 2022","author":"M Maarand","year":"2022","unstructured":"Maarand, M., Beyer, Y., K\u00e5sen, A., Fosseide, K.T., Kermorvant, C.: A comprehensive comparison of open-source libraries for handwritten text recognition in Norwegian. In: Uchida, S., Barney, E., Eglin, V. (eds.) DAS 2022. LNCS, vol. 13237, pp. 399\u2013413. Springer, Heidelberg (2022). https:\/\/doi.org\/10.1007\/978-3-031-06555-2_27"},{"key":"10_CR19","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s100320200071","volume":"5","author":"UV Marti","year":"2002","unstructured":"Marti, U.V., Bunke, H.: The IAM-database: an English sentence database for offline handwriting recognition. Int. J. Doc. Anal. Recognit. 5, 39\u201346 (2002). https:\/\/doi.org\/10.1007\/s100320200071","journal-title":"Int. J. Doc. Anal. Recognit."},{"key":"10_CR20","series-title":"CCIS","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-981-99-8181-6_6","volume-title":"Neural Information Processing","author":"Z Min","year":"2024","unstructured":"Min, Z., Wang, J.: Exploring the integration of large language models into automatic speech recognition systems: an empirical study. In: Luo, B., Cheng, L., Wu, Z.G., Li, H., Li, C. (eds.) ICONIP 2023. CCIS, vol. 1968, pp. 69\u201384. Springer, Singapore (2024). https:\/\/doi.org\/10.1007\/978-981-99-8181-6_6"},{"key":"10_CR21","doi-asserted-by":"publisher","unstructured":"Neto, A.F.S., Bezerra, B.L.D., Toselli, A.H., Lima, E.B.: A robust handwritten recognition system for learning on different data restriction scenarios. Pattern Recognit. Lett. 1, 1\u20137 (2022). https:\/\/doi.org\/10.1016\/j.patrec.2022.04.009","DOI":"10.1016\/j.patrec.2022.04.009"},{"key":"10_CR22","doi-asserted-by":"publisher","unstructured":"Nguyen, T.T.H., Jatowt, A., Coustaty, M., Doucet, A.: Survey of post-OCR processing approaches. ACM Comput. Surv. 54(6) (2021). https:\/\/doi.org\/10.1145\/3453476","DOI":"10.1145\/3453476"},{"key":"10_CR23","doi-asserted-by":"publisher","unstructured":"Puigcerver, J.: Are multidimensional recurrent layers really necessary for handwritten text recognition? In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a01, pp. 67\u201372 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.20","DOI":"10.1109\/ICDAR.2017.20"},{"key":"10_CR24","doi-asserted-by":"publisher","unstructured":"Roy, A., et al.: N-grammer: augmenting transformers with latent n-grams (2022). https:\/\/doi.org\/10.48550\/arXiv.2207.06366","DOI":"10.48550\/arXiv.2207.06366"},{"key":"10_CR25","doi-asserted-by":"publisher","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Erk, K., Smith, N.A. (eds.) Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Berlin, Germany, pp. 1715\u20131725. Association for Computational Linguistics (2016). https:\/\/doi.org\/10.18653\/v1\/P16-1162","DOI":"10.18653\/v1\/P16-1162"},{"key":"10_CR26","doi-asserted-by":"publisher","unstructured":"Soper, E., Fujimoto, S., Yu, Y.Y.: BART for post-correction of OCR newspaper text. In: Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021), pp. 284\u2013290. Association for Computational Linguistics, Online (2021). https:\/\/doi.org\/10.18653\/v1\/2021.wnut-1.31","DOI":"10.18653\/v1\/2021.wnut-1.31"},{"key":"10_CR27","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1007\/978-3-031-41679-8_11","volume-title":"Document Analysis and Recognition - ICDAR 2023","author":"S Tarride","year":"2023","unstructured":"Tarride, S., Boillet, M., Kermorvant, C.: Key-value information extraction from full handwritten pages. In: Fink, G.A., Jain, R., Kise, K., Zanibbi, R. (eds.) ICDAR 2023. LNCS, vol. 14188, pp. 185\u2013204. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-41679-8_11"},{"key":"10_CR28","doi-asserted-by":"crossref","unstructured":"Tarride, S., Schneider, Y., Generali, M., Boillet, M., Abadie, B., Kermorvant, C.: Improving automatic text recognition with language models in the pylaia open-source library. In: Submitted at ICDAR (2024)","DOI":"10.1007\/978-3-031-70549-6_23"},{"key":"10_CR29","doi-asserted-by":"publisher","unstructured":"Tassopoulou, V., Retsinas, G., Maragos, P.: Enhancing handwritten text recognition with n-gram sequence decomposition and multitask learning. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 10555\u201310560. IEEE Computer Society, Los Alamitos (2021). https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412351","DOI":"10.1109\/ICPR48806.2021.9412351"},{"key":"10_CR30","doi-asserted-by":"publisher","unstructured":"Voigtlaender, P., Doetsch, P., Ney, H.: Handwriting recognition with large multidimensional long short-term memory recurrent neural networks. In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 228\u2013233 (2016). https:\/\/doi.org\/10.1109\/ICFHR.2016.0052","DOI":"10.1109\/ICFHR.2016.0052"},{"key":"10_CR31","unstructured":"Wang, D., et al.: DocLLM: a layout-aware generative language model for multimodal document understanding (2023)"},{"key":"10_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1007\/978-3-030-01231-1_23","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Wigington","year":"2018","unstructured":"Wigington, C., Tensmeyer, C., Davis, B., Barrett, W., Price, B., Cohen, S.: Start, follow, read: end-to-end full-page handwriting recognition. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 372\u2013388. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_23"},{"key":"10_CR33","doi-asserted-by":"publisher","unstructured":"Xu, H., et al.: A pruned RNNLM lattice-rescoring algorithm for automatic speech recognition. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5929\u20135933 (2018). https:\/\/doi.org\/10.1109\/ICASSP.2018.8461974","DOI":"10.1109\/ICASSP.2018.8461974"},{"key":"10_CR34","doi-asserted-by":"publisher","unstructured":"Yousef, M., Bishop, T.E.: Origaminet: weakly-supervised, segmentation-free, one-step, full page textrecognition by learning to unfold. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01472","DOI":"10.1109\/CVPR42600.2020.01472"},{"key":"10_CR35","doi-asserted-by":"publisher","unstructured":"Zhang, H., Liang, L., Jin, L.: SCUT-HCCDoc: a new benchmark dataset of handwritten chinese text in unconstrained camera-captured documents. Pattern Recognit. 107559 (2020). https:\/\/doi.org\/10.1016\/j.patcog.2020.107559","DOI":"10.1016\/j.patcog.2020.107559"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70552-6_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,15]],"date-time":"2025-06-15T14:07:45Z","timestamp":1749996465000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70552-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031705519","9783031705526"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70552-6_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"11 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2024.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}