BibTeX

@inProceedings{berdicevskis-2020-older-290636,
	title        = {Older English Words Are More Polysemous},
	booktitle    = {The Evolution of Language: Proceedings of the 13th International Conference (EvoLang13). Pp. 14-21},
	author       = {Berdicevskis, Aleksandrs},
	year         = {2020},
	publisher    = {The Evolution of Language Conferences },
	address      = {Nijmegen },
}

@inProceedings{dannells-simon-2020-supervised-289944,
	title        = {Supervised OCR Post-Correction of Historical Swedish Texts: What Role Does the OCR System Play?},
	abstract     = {Current approaches for post-correction of OCR errors offer solutions that are tailored to a specific OCR system. This can be problematic if the post-correction method was trained on a specific OCR
system but have to be applied on the result of another system. Whereas OCR post-correction of historical text has received much attention lately, the question of what role does the OCR system play for the post-correction method has not been addressed. In this study we explore a dataset of
400 documents of historical Swedish text which has been OCR processed by three state-of-the-art OCR systems: Abbyy Finereader, Tesseract and Ocropus. We examine the OCR results of each system and present a supervised machine learning post-correction method that tries to approach
the challenges exhibited by each system. We study the performance of our method by using three evaluation tools: PrimA, Språkbanken evaluation tool and Frontiers Toolkit. Based on the evaluation analysis we discuss the impact each of the OCR systems has on the results of the post-
correction method. We report on quantitative and qualitative results showing varying degrees of OCR post-processing complexity that are important to consider when developing an OCR post-correction method.},
	booktitle    = {Proceedings of the Digital Humanities in the Nordic Countries, 5th Conference, Riga, Latvia, October 21-23, 2020},
	editor       = {Sanita Reinsone and Inguna Skadiņa and Anda Baklāne and Jānis Daugavietis},
	author       = {Dannélls, Dana and Simon, Persson},
	year         = {2020},
	publisher    = {CEUR-WS},
}

@inProceedings{lange-ljunglof-2020-learning-291243,
	title        = {Learning Domain-specific Grammars from a Small Number of Examples},
	abstract     = {In this paper we investigate the problem of grammar inference from a different perspective. The common approach is to try to infer a grammar directly from example sentences, which either requires a large training set or suffers from bad accuracy. We instead view it as a problem of grammar restriction or sub-grammar extraction. We start from a large-scale resource grammar and a small number of examples, and find a sub-grammar that still covers all the examples. To do this we formulate the problem as a constraint satisfaction problem, and use an existing constraint solver to find the optimal grammar. We have made experiments with English, Finnish, German, Swedish and Spanish, which show that 10–20 examples are often sufficient to learn an interesting domain grammar. Possible applications include computer-assisted language learning, domain-specific dialogue systems, computer games, Q/A-systems, and others.},
	booktitle    = {12th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI},
	author       = {Lange, Herbert and Ljunglöf, Peter},
	year         = {2020},
	publisher    = {SciTePress},
	ISBN         = {978-989-758-395-7},
}

@inProceedings{rouces-etal-2020-creating-290695,
	title        = {Creating an Annotated Corpus for Aspect-Based Sentiment Analysis in Swedish},
	abstract     = {Aspect-Based Sentiment Analysis constitutes a more fine-grained alternative to traditional sentiment analysis at sentence level. In addition to a sentiment value denoting how positive or negative a particular opinion or sentiment expression is, it identifies additional aspects or 'slots' that characterize the opinion. Some typical aspects are target and source, i.e. who holds the opinion and about which entity or aspect is the opinion. We present a large Swedish corpus annotated for Aspect-Based Sentiment Analysis. Each sentiment expression is annotated as a tuple that contains the following fields: one among 5 possible sentiment values, the target, the source, and whether the sentiment expressed is ironic.  In addition, the linguistic element that conveys the sentiment is identified too. Sentiment for a particular topic is also annotated at title, paragraph and document level.
The documents are articles obtained from two Swedish media (Svenska Dagbladet and Aftonbladet) and one online forum (Flashback), totalling around 4000 documents. The corpus is freely available and we plan to use it for training and testing an Aspect-Based Sentiment Analysis system.},
	booktitle    = {Proceedings of the 5th conference in Digital Humanities in the Nordic Countries, Riga, Latvia, October 21-23, 2020.},
	author       = {Rouces, Jacobo and Borin, Lars and Tahmasebi, Nina},
	year         = {2020},
	publisher    = {CEUR Workshop Proceedings},
}