To understand how stories are structured, we would like to be able to analyze the architecture of narratives. This article reviews and compares existing annotation guidelines for scene and narrative level annotation. We propose new guidelines, based on existing ones, and show how these can be effectively extended from general-purpose to specialized contexts, such as mystery novels which feature unique narrative elements like red herrings and plot twists. This provides a controlled environment for examining genre-specific event structuring. Additionally, we present a newly annotated genre-specific dataset of mystery novels, offering valuable resources for training and evaluating models in narrative understanding. This study aims to enhance annotation practices and advance the development of computational models for narrative analysis.

This article discusses the adaptation of traditional English readability measures into Sesotho, a Southern African indigenous low-resource language. We employ the use of a translated readability corpus to extract textual features from the Sesotho texts and readability levels from the English translations. We look at the correlation between the different features to ensure that non-competing features are used in the readability metrics. Next, through linear regression analyses, we examine the impact of the text features from the Sesotho texts on the overall readability levels (which are gauged from the English translations). Starting from the structure of the traditional English readability measures, linear regression models identify coefficients and intercepts for the different variables considered in the readability formulas for Sesotho. In the end, we propose ten readability formulas for Sesotho (one more than the initial nine; we provide two formulas based on the structure of the Gunning Fog index). We also introduce intercepts for the Gunning Fog index, the Läsbarhets index and the Readability index (which do not have intercepts in the English variants) in the Sesotho formulas.

Identifying the high level structure of texts provides important information when performing distant reading analysis. The structure of texts is not necessarily linear, as transitions, such as changes in the scenery or flashbacks, can be present. As a first step in identifying this structure, we aim to identify transitions in texts. Previous work (Heyns and van Zaanen, 2021) proposed a system that can successfully identify one transition in literary texts. The text is split in snippets and LDA is applied, resulting in a sequence of topics. A transition is introduced at the point that separates the topics (before and after the point) best. In this article, we extend the existing system such that it can detect multiple transitions. Additionally, we introduce a new system that inherently handles multiple transitions in texts. The new system also relies on LDA information, but is more robust than the previous system. We apply these systems to texts with known transitions (as they are constructed by concatenating text snippets stemming from different source texts) and evaluation both systems on texts with one transition and texts with two transitions. As both systems rely on LDA to identify transitions between snippets, we also show the impact of varying the number of LDA topics on the results as well. The new system consistently outperforms the previous system, not only on texts with multiple transitions, but also on single boundary texts.

Revision plays a major role in writing and the analysis of writing processes. Revisions can be analyzed using a product-oriented approach (focusing on a finished product, the text that has been produced) or a process-oriented approach (focusing on the process that the writer followed to generate this product). Although several language resources exist for the product-oriented approach to revisions, there are hardly any resources available yet for an in-depth analysis of the process of revisions. Therefore, we provide an extensive dataset on revisions made during writing (accessible via https://hdl.handle.net/10411/VBDYGX). This dataset is based on keystroke data and eye tracking data of 65 students from a variety of backgrounds (undergraduate and graduate English as a first language and English as a second language students) and a variety of tasks (argumentative text and academic abstract). In total, 7,120 revisions were identified in the dataset. For each revision, 18 features have been manually annotated and 31 features have been automatically extracted. As a case study, we show two potential use cases of the dataset. In addition, future uses of the dataset are described.

Languages vary in the way stress is assigned to syllables within words. This article investigates the learnability of stress systems in a wide range of languages. The stress systems can be described using finite-state automata with symbols indicating levels of stress (primary, secondary, or no stress). Finite-state automata have been the focus of research in the area of grammatical inference for some time now. It has been shown that finite-state machines are learnable from examples using state-merging. One such approach, which aims to learn k-testable languages, has been applied to stress systems with some success. The family of k-testable languages has been shown to be efficiently learnable (in polynomial time). Here, we extend this approach to k, l-local languages by taking not only left context, but also right context, into account. We consider empirical results testing the performance of our learner using various amounts of context (corresponding to varying definitions of phonological locality). Our results show that our approach of learning stress patterns using state-merging is more reliant on left context than on right context. Additionally, some stress systems fail to be learned by our learner using either the left-context k-testable or the left-and-right-context k, l-local learning system. A more complex merging strategy, and hence grammar representation, is required for these stress systems.

In most languages, new words can be created through the process of compounding, which combines two or more words into a new lexical unit. Whereas in languages such as English the components that make up a compound are separated by a space, in languages such as Finnish, German, Afrikaans and Dutch these components are concatenated into one word. Compounding is very productive and leads to practical problems in developing machine translators and spelling checkers, as newly formed compounds cannot be found in existing lexicons. The Automatic Compound Processing (AuCoPro) project deals with the analysis of compounds in two closely-related languages, Afrikaans and Dutch. In this paper, we present the development and evaluation of two datasets, one for each language, that contain compound words with annotated compound boundaries. Such datasets can be used to train classifiers to identify the compound components in novel compounds. We describe the process of annotation and provide an overview of the annotation guidelines as well as global properties of the datasets. The inter-rater agreements between the annotators are considered highly reliable. Furthermore, we show the usability of these datasets by building an initial automatic compound boundary detection system, which assigns compound boundaries with approximately 90% accuracy.