The Word Rain visualisation technique is a development of the classic word cloud, providing more possibilities for analysis of the texts visualised. We here briefly describe the work carried out so far, the reasoning behind it, and what could lie ahead.

The classic word cloud remains a popular visualisation technique, also to use for more advanced text exploration and comparison tasks. However, since the standard word cloud does not provide any support for these kinds of analytical tasks, we have created the Word Rain visualisation technique, which is a development of the classic word cloud. The Word Rain technique positions paradigmatically similar words close to each other on the x-axis, which makes it easier to identify semantic word clusters and to carry out comparison tasks. We have previously applied the technique on several different tasks, and we here show how the Word Rain visualisation can support a topical analysis of the text collection content. We first apply the topic modelling tool Topics2Themes to a collection of texts on the subject of climate change, and then use the Word Rain technique to visualise the automatically extracted topics. The Word Rain visualisation applied on the entire text collection provides an overview of its content, sorted according to paradigmatic similarity. When also creating focused word rain visualisations for the extracted topics, a visual semantic profile for each one of the topics is created, which supports the tasks of understanding and comparing topics. We have, thereby, here provided yet an example of how the Word Rain technique can be practically used for visualising and exploring texts.

Word Rain is a novel approach to the classic word cloud that uses word embeddings to make it useful for exploring the word content of a text or corpus. Downloading and running the code can, however, be prohibitively difficult or cumbersome for non-technical users and casual evaluation. Since Word Rain also requires a word embeddings model, the inexperienced or casual user would benefit greatly from a streamlined interface. We have therefore collected everything that is needed in a web based service and are making it available as a SWELANG K-centre resource.

Yiddish is one of the national minority languages of Sweden, and one of the languages for which the Swedish Institute for Language and Folklore is responsible for developing useful language resources. We here describe the web-based version of a Swedish–Yiddish/Yiddish–Swedish dictionary. The single search field of the web-based dictionary is used for incrementally searching all three components of the dictionary entries (the word in Swedish, the word in Yiddish with Hebrew characters and the transliteration in Latin script). When the user accesses the dictionary in an online mode, the dictionary is saved in the web browser, which makes it possible to also use the dictionary offline.

We applied the topic modelling tool Topics2Themes to a collection of German tweets on the subject of climate change. Topics2Themes is currently being further developed and evaluated within Spr{\aa}kbanken Sam, which is a part of {\sc SWE-CLARIN}.  The tool automatically extracted 15 topics from the tweet collection. We used the graphical user interface of Topics2Themes to manually search for recurring themes among the eight tweets most closely associated with the topics extracted. Although the content of the tweets associated with a topic was often diverse, we were still able to identify recurring themes. More specifically, 14 themes that occurred at least three times were identified in the texts analysed.

Rikstermbanken (Sweden’s National Term Bank), which was launched in 2009, uses the Nordic Terminological Record Format (NTRF) for organising its terminological data. Since then, new terminology formats have been established as standards, e.g., the Termbase eXchange format (TBX). We here describe work carried out by the Institute for Language and Folklore within the Federated eTranslation TermBank Network Action. This network develops a technical infrastructure for facilitating sharing of terminology resources throughout Europe. To be able to share some of the term collections of Rikstermbanken within this network and export them to Eurotermbank, we have implemented a conversion from the Nordic Terminological Record Format, as used in Rikstermbanken, to the TBX format.

We here demonstrate how a set of tools that are being maintained and further developed within the Språkbanken Sam and SWE-CLARIN infrastructures can be employed for creating manually labelled training data in a low-resource setting. As example text, we used the “COVID-19 Open Research Dataset”, and created manually annotated training data for its associated Kaggle task,“What do we know about COVID-19 risk factors?”. We first used our topic modelling tool to i) select a text set for manual annotation, ii) classify the texts into preliminary classification categories, and iii) analyse the texts in search for potential refinements of the annotation categories. We then annotated the text set on a more granular level by labelling the token sequences that indicated the existence of the refined categories in the text. Finally, we used the granularly annotated text set as a seed set, and applied our active learning tool for actively selecting additional texts for annotation. For the token-sequence annotations, we used our text annotation tool, which includes support for incorporating automatic pre-annotations.

A topic modelling tool was adapted to requirements for a collection of Swedish folk legends. To offer an overview of a list of folk legend texts, which had been automatically extracted by the topic modelling tool, snippet text versions of the folk legends were displayed. The snippets were constructed from the full-text versions of the legends using the sentences most relevant to the topics extracted by the topic modelling algorithm. In addition, collection-adapted data was constructed for performing a pre-processing of the folk legend texts, before they were submitted to the topic modelling algorithm. This data consisted of a collection-adapted stop word list and word lists for improving the quality of clusters of semantically similar words.