In the experiments briefly presented in this abstract, we compare the performance of a generalist Swedish pre-trained language model with a domain-specific Swedish pre-trained model on the downstream task of focussed terminology extraction of implant terms, which are terms that indicate the presence of implants in the body of patients. The fine-tuning is identical for both models. For the search strategy we rely on KD-Tree that we feed with two different lists of term seeds, one with noise and one without noise. Results shows that the use of a domain-specific pre-trained language model has a positive impact on focussed terminology extraction only when using term seeds without noise.

In this paper, we present the current version of The Swedish Simplification Toolkit. The toolkit includes computational and empirical tools that have been developed along the years to explore a still neglected area of NLP, namely the simplification of “standard” texts to meet the needs of target audiences. Target audiences, such as people affected by dyslexia, aphasia, autism, but also children and second language learners, require different types of text simplification and adaptation. For example, while individual with aphasia have difficulties in reading compounds (such as arbetsmarknadsdepartement, eng. ministry of employment), second language learners struggle with cultural-specific vocabulary (e.g. konflikträdd, eng. afraid of conflicts). The toolkit allows user to selectively decide the types of simplification that meet the specific needs of the target audience they belong to. The Swedish Simplification Toolkit is one of the first attempts to overcome the one-fits-all approach that is still dominant in Automatic Text Simplification, and proposes a set of computational methods that, used individually or in combination, may help individuals reduce reading (and writing) difficulties.

Privacy preservation of sensitive information is one of the main concerns in clinical text mining. Due to the inherent privacy risks of handling clinical data, the clinical corpora used to create the clinical Named Entity Recognition (NER) models underlying clinical de-identification systems cannot be shared. This situation implies that clinical NER models are trained and tested on data originating from the same institution since it is rarely possible to evaluate them on data belonging to a different organization. These restrictions on sharing make it very difficult to assess whether a clinical NER model has overfitted the data or if it has learned any undetected biases. This paper presents the results of the first-ever cross-institution evaluation of a Swedish de-identification system on Swedish clinical data. Alongside the encouraging results, we discuss differences and similarities across EHR naming conventions and NER tagsets.

In this paper, we compare the performance of two BERT-based text classifiers whose task is to classify patients (more precisely, their medical histories) as having or not having implant(s) in their body. One classifier is a fully-supervised BERT classifier. The other one is a semi-supervised GAN-BERT classifier. Both models are compared against a fully-supervised SVM classifier. Since fully-supervised classification is expensive in terms of data annotation, with the experiments presented in this paper, we investigate whether we can achieve a competitive performance with a semi-supervised classifier based only on a small amount of annotated data. Results are promising and show that the semi-supervised classifier has a competitive performance with the fully-supervised classifier.

In this paper, we propose visualizing results of a corpus-based study on text complexity using radar charts. We argue that the added value of this type of visualisation is the polygonal shape that provides an intuitive grasp of text complexity similarities across the registers of a corpus. The results that we visualize come from a study where we explored whether it is possible to automatically single out different facets of text complexity across the registers of a Swedish corpus. To this end, we used factor analysis as applied in Biber’s Multi-Dimensional Analysis framework. The visualization of text complexity facets with radar charts indicates that there is correspondence between linguistic similarity and similarity of shape across registers.

We explore the effectiveness of four feature representations – bag-of-words, word embeddings, principal components and autoencoders – for the binary categorization of the easy-to-read variety vs standard language. Standard language refers to the ordinary language variety used by a population as a whole or by a community, while the “easy-to-read” variety is a simpler (or a simplified) version of the standard language. We test the efficiency of these feature representations on three corpora, which differ in size, class balance, unit of analysis, language and topic. We rely on supervised and unsupervised machine learning algorithms. Results show that bag-of-words is a robust and straightforward feature representation for this task and performs well in many experimental settings. Its performance is equivalent or equal to the performance achieved with principal components and autoencorders, whose preprocessing is however more time-consuming. Word embeddings are less accurate than the other feature representations for this classification task.

We present initial results from an international and multi-disciplinary research collaboration that aims at the construction of a reference corpus of web genres. The primary application scenario for which we plan to build this resource is the automatic identification of web genres. Web genres are rather difficult to capture and to describe in their entirety, but we plan for the finished reference corpus to contain multi-level tags of the respective genre or genres a web document or a website instantiates. As the construction of such a corpus is by no means a trivial task, we discuss several alternatives that are, for the time being, mostly based on existing collections. Furthermore, we discuss a shared set of genre categories and a multi-purpose tool as two additional prerequisites for a reference corpus of web genres.

In this paper, we present an inferential model for text type and genre identification of Web pages, where text types are inferred using a modified form of Bayes’ theorem, and genres are derived using a few simple if-then rules. As the genre system on the Web is a complex phenomenon, and Web pages are usually more unpredictable and individualized than paper documents, we propose this approach as an alternative to unsupervised and supervised techniques. The inferential model allows a classification that can accommodate genres that are not entirely standardized, and is more capable of reading a Web page, which is mixed, rarely corresponding to an ideal type and often showing a mixture of genres or no genre at all. A proper evaluation of such a model remains an open issue.

The Web has triggered many adjustments in many fields. It also has had a strong impact on the genre repertoire. Novel genres have already emerged, e.g. blog and FAQs. Presumably, other new genres are still in formation, because the Web is still fluid and in constant change. In this paper we present an experiment that explores the possibility of automatically detecting the emerging textual patterns that are slowly taking shape on the Web. Emerging textual patterns can develop into novel Web genres or novel text types in the near future. The experimental set up includes a collection of unclassified web pages, two sets of features and the use of cluster analysis. Results are encouraging and deserve further investigation.