Assessing the Impact of OCR Quality on Downstream NLP Tasks
| Autor: | van Strien, D., Beelen, K., Coll Ardanuy, M., Hosseini, K., McGillivray, B., Colavizza, G., Rocha, A., Steels, L., van den Herik, J. |
|---|---|
| Přispěvatelé: | AIHR (FGw), Language and Computation (ILLC, FNWI/FGw), ILLC (FGw) |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Topic model
business.industry Process (engineering) Computer science media_common.quotation_subject Volume (computing) Optical character recognition computer.software_genre NLP Digital Humanities OCR Optical Character Recognition Named-entity recognition Dependency grammar Information Retrieval ComputingMethodologies_DOCUMENTANDTEXTPROCESSING Quality (business) Artificial intelligence Language model business computer Natural language processing Natural Language Processing media_common |
| Zdroj: | ICAART 2020: proceedings of the 12th International Conference on Agents and Artificial Intelligence : Valletta, Malta, February 22-24, 2020, 1, 484-496 ICAART (1) |
| Popis: | A growing volume of heritage data is being digitized and made available as text via optical character recognition (OCR). Scholars and libraries are increasingly using OCR-generated text for retrieval and analysis. However, the process of creating text through OCR introduces varying degrees of error to the text. The impact of these errors on natural language processing (NLP) tasks has only been partially studied. We perform a series of extrinsic assessment tasks — sentence segmentation, named entity recognition, dependency parsing, information retrieval, topic modelling and neural language model fine-tuning — using popular, out-of-the-box tools in order to quantify the impact of OCR quality on these tasks. We find a consistent impact resulting from OCR errors on our downstream tasks with some tasks more irredeemably harmed by OCR errors. Based on these results, we offer some preliminary guidelines for working with text produced through OCR. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|