Search

The aim of this article is to offer a systematic review of digital studies that provide new research perspectives on ancient classical theatre. The undeniable progress in the field of computational analysis in the service of traditional textual interpretation is helping to study in greater depth and to interpret in greater detail the classical linguistic corpora that have come down to us through the manuscript tradition. The new model of digital research is integrated not only in the field of information technologies, but also in the field of e-learning, where we can already observe the implementation of a new educational model. Based on the digital processing of data on Greco-Roman theatre, a systematic review is presented, following the methodological principles of the PRISMA statement [ Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2009 (2020)]. [ABSTRACT FROM AUTHOR]

This research focuses on classifying translated and non-translated Chinese texts by analyzing syntactic rule features, using an integrated approach of machine learning and entropy analysis. The methodology employs information entropy to gauge the complexity of syntactic rules in both text types. The methodology is based on the concept of information entropy, which serves as a quantitative measure for the complexity inherent in syntactic rules as manifested from tree-based annotations. The goal of the study is to explore whether translated Chinese texts demonstrate syntactic characteristics that are significantly different from those of non-translated texts, thereby permitting a reliable classification between the two. To do this, the research calculates information entropy values for syntactic rules in two comparable corpora, one of translated and the other of non-translated Chinese texts. Then, various machine learning models are applied to these entropy metrics to identify any significant differences between the two groups. The results show significant differences in the syntactic structures. Translated texts have a higher degree of entropy, indicating more complex syntactic constructs compared to non-translated texts. These findings contribute to our understanding of the effect of translation on language syntax, with implications for text classification and translation studies. [ABSTRACT FROM AUTHOR]

Contemporary Japanese given names exhibit great variety and have minimal formal restrictions in their formation. It is often possible, however, to determine the gender of the name's bearer from its phonological and/or graphic form. In this article, various features, including name length, syllables, and characters at particular positions within a name and the choice of script, are statistically analyzed to determine whether they are significantly associated with male or female names and which of them contribute the most to the expression of gender. The findings of this study verify the empirical knowledge of the gender-markedness of some of the features and establish a solid foundation for future feature-based gender prediction algorithms. The expression of gender in currently bestowed names is discussed in the context of major changes in naming practices and name choices toward the end of the 20th century. [ABSTRACT FROM AUTHOR]

Although the idea of the Anthropocene originated in the earth sciences, there have been increasing calls for questions about the Anthropocene to be addressed by pan-disciplinary groups of researchers from across the natural sciences, social sciences, and humanities. We use data analysis techniques from corpus linguistics to examine academic texts about the Anthropocene from these disciplinary families. We read the data to suggest that barriers to a broadly interdisciplinary study of the Anthropocene are high, but we are also able to identify some areas of common ground that could serve as interdisciplinary bridges. [ABSTRACT FROM AUTHOR]

We describe an efficient pipeline for morpho-syntactically annotating an ancient language corpus which takes advantage of bootstrapping techniques. This pipeline is designed for ancient language scholars looking to jump-start their own treebank projects, which can in turn serve further pedagogical research projects in the target language. We situate our work in the field of similar ancient language treebank projects, arguing that our approach shows that individual humanities scholars can leverage current machine-learning tools to produce their own richly annotated corpora. We illustrate this pipeline by producing a new Akkadian-language treebank based on two volumes from the online editions of the State Archives of Assyria project hosted on Oracc, as well as a spaCy language model named AkkParser trained on that treebank. Both of these are made publicly available for annotating other Akkadian corpora. In addition, we discuss linguistic issues particular to the Neo-Assyrian letter corpus and data-encoding complications of cuneiform texts in Oracc. The strategies, language models, and processing scripts we developed to handle both linguistic and data-encoding issues in this project will be of special interest to scholars seeking to develop their own cuneiform treebanks. [ABSTRACT FROM AUTHOR]

The analysis of co-citations, which occurs when two publications or authors are mentioned together in the same text, has long been established as a practice within scientometrics, particularly in the field of "science mapping". However, historiography has shown less openness to utilizing co-citation analysis for distant reading purposes. To address this gap, this article presents a comprehensive methodology for applying co-citation analysis to extensive collections of historical documents, specifically 17th-century letters indexed in the ePistolarium database. In science mapping, co-citation serves as an indicator for tracking the development of scientific fields. Similarly, I employ co-citation to map the Dutch socio-intellectual landscape during the Scientific Revolution period (1623–87) and evaluate the strengths and limitations of this approach. [ABSTRACT FROM AUTHOR]

This article introduces and explores the 3.5-million-word Victorian Anti-Vaccination Discourse Corpus (VicVaDis). The corpus is intended to provide a (freely accessible) historical resource for the investigation of the earliest public concerns and arguments against vaccination in England, which revolved around compulsory vaccination against smallpox in the second half of the 19th century. It consists of 133 anti-vaccination pamphlets and publications gathered from 1854 to 1906, a span of 53 years that loosely coincides with the Victorian era (1837–1901). This timeframe was chosen to capture the period between the 1853 Vaccination Act, which made smallpox vaccination for babies compulsory, and the 1907 Act that effectively ended the mandatory nature of vaccination. After an overview of the historical background, this article describes the rationale, design and construction of the corpus, and then demonstrates how it can be exploited to investigate the main arguments against compulsory vaccination by means of widely accessible corpus linguistic tools. Where appropriate, parallels are drawn between Victorian and 21st-century vaccine-hesitant attitudes and arguments. Overall, this article demonstrates the potential of corpus analysis to add to our understanding of historical concerns about vaccination. [ABSTRACT FROM AUTHOR]

The year 1993 represents a momentous milestone in the not-so-long history of translation and interpreting studies (TIS). The foundational paper published by Mona Baker entitled 'Corpus linguistics and translation studies: Implications and applications' in 1993 has signalled a defining moment in the application of digital humanities (DH) approaches in TIS. Since then, corpus-based TIS, as a most visible manifestation of DH in TIS, has come into being and is now gradually entering into maturity. Compared with the previously largely anecdotal, impressionist, and prescriptivist accounts of translation and interpreting, the incorporation of DH tools (e.g. CL) has significantly enriched TIS with new perspectives. This makes it possible for researchers to explore the various aspects of translation and interpreting in a more objective and systematic way, drawing on real-world data. Now one-third of a century has passed since the publication of Baker's seminal paper, DH-inspired studies of translation and interpreting are in full swing. As we are reaching the 30-year mark of the influential publication, it is important for us to take stock of the previous achievements and look to the future both with pride and a cool head. In this article, we trace the developments of a DH approach to TIS and present the state of the art, before discussing some of the limitations and pitfalls and the road ahead going forward. [ABSTRACT FROM AUTHOR]

With the rapid growth of online content written in the Kurdish language, there is an increasing need to make it machine-readable and processable. Part of speech (POS) tagging is a critical aspect of natural language processing (NLP), playing a significant role in applications such as speech recognition, natural language parsing, information retrieval, and multiword term extraction. This study details the creation of the DASTAN corpus, the first POS-annotated corpus for the Sorani Kurdish dialect. The corpus, containing 74,258 words and thirty-eight tags, employs a hybrid approach utilizing the bigram hidden Markov model in combination with the Kurdish rule-based approach to POS tagging. This approach addresses two key problems that arise with rule-based approaches, namely misclassified words and ambiguity-related unanalyzed words. The proposed approach's accuracy was assessed by training and testing it on the DASTAN corpus, yielding a 96% accuracy rate. Overall, this study's findings demonstrate the effectiveness of the proposed hybrid approach and its potential to enhance NLP applications for Sorani Kurdish. [ABSTRACT FROM AUTHOR]

This article presents a method of emotion analysis for German drama from the 17th to the 19th century that significantly goes beyond previous research approaches in computational literary studies. It is based on annotations of 17 dramatic texts resulting in 11,939 annotations which were used as training material to fine-tune a German language BERT model that achieves an average accuracy of 73% for the single-label emotion classification of fourteen emotion types in cross-validation. We apply the emotion classification on a corpus of 141 comedies and 92 tragedies to compare these genres. For tragedies, the mean proportion percentages of 'suffering' and 'abhorrence' are higher than for comedies. Inversely, mean percentages of 'anger' and 'joy' are higher for comedies than for tragedies. A new finding is the surprisingly high proportion of 'anger' in comedies. Emotion distribution of the last scenes in dramatic texts also proves the quality of the classified data in terms of literary studies. In addition, the emotion distribution for several subgenres of comedy is investigated including non-canonical works of wide circulation which reached the recipients directly through the depicted emotions in the Kasperl Plays. Comedies from 1740 to 1770 are characterized by a pairing of higher amounts of 'friendship' and 'love'. Satirical comedies from the same period stand out due to high rates of 'anger' as well as 'suffering'. The very successful Kasperl plays turn out to be characterized by a comparatively large percentage of 'schadenfreude' and 'joy'. [ABSTRACT FROM AUTHOR]

The fact is now accepted that specialised discourses do not deviate from the rules of language: variation in all its forms emerges from corpora. One of the questions that now arises is that of "implementing" socioterminological data in terminological resources: how can sociolinguistic diversity be integrated into a descriptive program? After reviewing the types of variation, this article explores an approach to integrating some of these data into a terminographic ressource. This will provide an opportunity to discuss the question of the interface with the corpus, which is no longer confined to a descriptive objective, but is likely to become a pivotal element of a database. [ABSTRACT FROM AUTHOR]

Bertalign is designed to improve sentence alignment accuracy for Chinese–English parallel corpora of literary texts. Aligning bilingual literary texts is not trivial, since most of the translation is interpretative and not based on 1-to-1 mappings between source and target sentences. Existing alignment methods highlight 1-to-1 links while having difficulty coping with 1-to-many and many-to-many alignments that are common in literary texts. To overcome the weaknesses of current approaches, we propose a novel two-step algorithm for bilingual sentence alignment. The first step finds the optimal paths for 1-to-1 alignments based on the top- k most semantically similar target sentences for each source sentence using the bidirectional encoder representations from transformer-based cross-lingual word embeddings. The second step relies on search paths found in the previous step to recover all valid alignments with more than one sentence on each side of the bilingual text. A comprehensive experiment was conducted on a newly built Chinese–English literary parallel corpus and a large-scale publicly available bilingual corpus of the Bible to compare the performance of Bertalign with five baseline systems: Gale-Church, Hunalign, Bleualign, Bleurtalign, and Vecalign. The results show that Bertalign achieves the highest accuracy in terms of F 1 score on the two evaluation datasets than previous methods. [ABSTRACT FROM AUTHOR]

The availability of large digital archives of historical newspaper content has transformed the historical sciences. However, the scale of these archives can limit the direct application of advanced text processing methods. Even if it is computationally feasible to apply sophisticated language processing to an entire digital archive, if the material of interest is a small fraction of the archive, the results are unlikely to be useful. Methods for generating smaller specialized corpora from large archives are required to solve this problem. This article presents such a method for historical newspaper archives digitized using the METS/ALTO XML standard (Veridian Software, n.d.). The method is an 'iterative bootstrapping' approach in which candidate corpora are evaluated using text mining techniques, items are manually labelled, and Naïve Bayes text classifiers are trained and applied in order to produce new candidate corpora. The method is illustrated by a case study that investigates philosophical content, broadly construed, in pre-1900 English-language New Zealand newspapers. Extensive code is provided in Supplementary Materials. [ABSTRACT FROM AUTHOR]

The aim of this study was to verify the possibility of Sor Juana Inés de la Cruz authoring the anonymous part of the baroque play La Segunda Celestina , commissioned to Agustín de Salazar, and left unfinished after his death. This is a first systematic stylometric study on this problem and a baroque hispanoamerican text. In our study, we faced building a balanced corpus from few available resources, and took extensive evaluation measures to deal with unclear stylometric signals. We use a variety of established attribution and verification methods, and introduce a novel evaluation procedure of examining historic texts with scarce corpora. The results support Sor Juana's authorship, and unravel new connections between her and other authors of the time, showing, still undermined, powerful impact of her works on the epoch. The solutions adopted in solving methodological problems of such a complex task show how stylometry can overcome similar challenges. [ABSTRACT FROM AUTHOR]

This article introduces the 'Environmental Scan' as answer to the question of hidden biases in digital heritage collections. Its substantive focus is digitized nineteenth-century British provincial newspapers, and in particular the JISC corpus, a popular, publicly-funded resource for scholars. While multiple papers have meticulously investigated the genesis of such newspaper collections, in the process highlighting the often unacknowledged politics of collection, preservation and dissemination via microfilm and now digitization, our aim is to explore questions of representativeness and bias in new ways by enriching computational analysis of digital corpora with the historical insights that can be derived from a contemporaneous reference source: namely, the Victorian newspaper press directories. [ABSTRACT FROM AUTHOR]

Given the growing expansion in the development and use of computational methods in humanities research, it is necessary to propose methodologies that properly explore the questions posed by different disciplines, considering the locality of both data and the process behind its generation. In the present work, we explore the problem of automatically identifying the main topics in collections of Nahua discourses known as huehuetlahtollis. Each document in the collections is introduced through an extended title, and it is a natural question if enhancing the role of title terms during the unsupervised learning process could enrich results. Aiming at explainability, we consider a model based on nonnegative matrix factorizations (NMF). An overview of the historical process behind the composition of the explored corpora suggests that titles reflect the point of view of the collection's compiler in manners that justify viewing the paratext as a supplementary source on the material. Therefore, we propose a bi-objective NMF scheme that appropriately reflects the a priori knowledge on the corpus, linking and combining the information of titles and content to improve the accuracy in identifying topic groups and relevant terms within a corpus. By comparing three different schemes against the labels assigned by an expert, we show that our model better reflects the nature of data, translating into higher accuracy. Finally, we present some insights on the studied corpora derived from our analysis of identified relevant terms. [ABSTRACT FROM AUTHOR]

A distant-reading task in literary corpus analysis is to group stylometrically similar texts. Since there are many ways to define writing style, the result not only depends on the clustering method but even more so on the measure of similarity. With authorship attribution, the predominant application of stylometry, as its benchmark much research has addressed the utility of methods for measuring similarity. We use a corpus of German-language novellas to demonstrate that one may be interested in very different meaningful groups of texts simultaneously, and that these can be recovered from stylometric clustering if the measure is chosen accordingly. As can be expected, different measures do better at recovering groups associated with, for instance, subgenre, author gender, or narrative perspective. As a consequence, it is suggested that corpus analyses should not be based on what is currently considered the most refined measure of stylometric similarity, but rather break down the decisions that yield a specific measure and provide substantively justified arguments for them. [ABSTRACT FROM AUTHOR]

Our article reports on the emerging Corpus of Contemporary Czech Poetry and the possibilities for its use. We describe the genesis of the idea of creating a specific corpus that combines the principles of synchronicity and genre instead of relying on the presence of poetry in the general corpus of contemporary Czech. We also characterize the structure of our corpus, which is designed to cover both of the basic media areas in which contemporary poetry is published and distributed: either in books or through open publishing platforms on the Internet (literary forums). We additionally describe the functionalities of the tools for mining the corpus data, which are designed to easily serve comparative analyses across media (print/web). We suggest how useful quantitative data analysis can be in the first phase of language-oriented literary research; or rather we point out the necessity of combining quantitative and qualitative approaches. Only the researcher's interpretative proficiency can decide on the boundaries of the field under study and the meaning of the elements present in it. In text-centred analyses, language corpora should start to play a similar role as other tools of scientific infrastructure, such as bibliographic databases. [ABSTRACT FROM AUTHOR]

The study examined contemporary Chinese novels that depicted the social changes in rural and urban areas. We analyzed the texts using several quantitative methods of stylometry (lexical richness, activity, descriptivity, nominality, cluster analysis of the most frequent words) and corpus linguistics (keywords). We focused on the differences (both in style and in content) between contemporary fiction depicting life in Chinese rural and urban areas. The results revealed that rural stories are more dynamic (active), focusing more on the plot with a simpler description and a smaller vocabulary. [ABSTRACT FROM AUTHOR]

This study examines the consistency of medieval abbreviation practices in a parallel corpus consisting of Latin and Middle English copies of a plague treatise attributed to John of Burgundy (JB). Focusing on different versions of the treatise enables us to maximize textual and lexical overlap, comparing differences caused by text type, word type, and language. We examine how the following variables affect the consistency of abbreviating across manuscript witnesses: A language: Latin versus English; B text type: recipes versus running text; C word type: lexical versus function words; and D: the number of characters in a word. Variables A–D are compared using a parallel corpus of automatically aligned rich TEI P5 XML-tagged transcriptions of six manuscript witnesses to the JB treatise. The alignment process is based on computer–human collaboration and custom-built alignment tool which uses sections tagged in the TEI XML file and word division. The results reveal that abbreviation was overwhelmingly more consistent in Latin than in the Middle English and somewhat more consistent in recipes. High token counts of frequent lexical items had a major effect on the results. Word length worked better than division into lexical and function words. [ABSTRACT FROM AUTHOR]

This article presents the elaboration of a morphosyntactically annotated diachronic corpus of Basque, and the first results obtained in the processing of historical varieties of this language with computational techniques. The corpus size is around one million words, expanding from the 15th to the mid-18th century and encompassing the most significant written production in all historical dialects. Morphosyntactic tagging allows for systematic searches at different levels of complexity; additionally, a rich set of metadata enables searches based on sociohistorical criteria too. This is not only the first tagged corpus of historical Basque but also a means to improve language processing tools by analyzing historical varieties more or less distant from the present-day standard language. Moreover, this project aims to set a model for further works in the historical corpora of Basque and inform similar projects on other languages. [ABSTRACT FROM AUTHOR]

Following the findings of two prior publications this supplement makes use of the General Imposters (GI) method which largely confirms previous results, namely that the Marlowe corpus is stylistically inhomogeneous. The two Tamburlaines match each other in style, but the remaining corpus has hardly any stylistic similarity with them. Instead, there are strong indications of Shakespeare's involvement in nominal Marlowe plays which becomes most obvious in The Jew of Malta. In terms of methodology, GI turns out to be an additional verification system, at its best when the training set consists of the texts of only two authors. [ABSTRACT FROM AUTHOR]

In this article, we argue for the benefits of combining large-scale analyses of visual materials currently pursued within digital humanities with insights from multimodality research, which is an emerging discipline that studies how human communication relies on appropriate combinations of expressive resources. We show that concepts developed within the field of multimodality research provide appropriate metadata schemes for various modes of expression in large corpora and datasets. We illustrate the proposed approach using a common mode of expression, diagrams, and analyse two recent multimodal diagram corpora using statistical and computational methods. Our results suggest that multimodally-motivated metadata schemes can provide a robust foundation for computational analyses of large corpora and datasets. Even if a corpus or dataset is not designed to support full-blown analyses of multimodal communication, our results imply that multimodality theory can still be used to impose tighter analytical control over a variety of visual materials. [ABSTRACT FROM AUTHOR]

The article focuses on the analysis of the user as an aesthetic category and proposes a methodology for evaluating user response within a framework that combines theoretical background from different areas, the theory of aesthetic response, psycholinguistics, appraisal theory, dialogism, and affective stylistics, with the application of digital tools for corpus linguistics and sentiment analysis. Four user types were derived from the corpus linguistics analysis referred to as immersed, distant, sceptical, and enthusiastic users. Each type may encompass a certain degree of intentionality and convey an attitude, implying features such as commitment and honesty, objectivity and engagement with the audience, critical reflection and circumspection, openness to technological novelty, and enjoyment. This assumes that the users involved in usability testing are not neutral or undifferentiated informational entities placed in an experimental context but individuals that respond to the same stimuli and express themselves differently in light of psycholinguistic factors and rules of social interaction. On the other hand, the results of sentiment analysis showed that an experiential analysis, centred not only on the artefact but also on the response and the experience it generates, may enable understanding the user as involved in a hermeneutic process of interpretation during his/her interaction with the studied artefact. Given the small scale of the analysed data, the study does not intend to provide evidence for general or definitive statements but formulates and illustrates a set of interpretative hypotheses and methodological directions for further enquiry aiming at developing an 'aesthetics' of user response. [ABSTRACT FROM AUTHOR]

This article aims to analyse aboutness in a corpus of videos posted by Brazilian female transsexual influencers. The analysis is based on Corpus Linguistics, machine learning techniques, and automated lexical mapping techniques, especially Topic Modelling. This technique served as a starting point for establishing four main topics: Relationship and Social Events, Gender, Beauty, and Transition. These topics had their statistically relevant lexis qualitatively analysed by concordance. This study used tools written in R and Python programming languages, made freely available to the community. The results show that the topics are qualitatively and quantitatively consistent, and the approach adopted was fruitful for text analysis. [ABSTRACT FROM AUTHOR]

The present paper uses corpus linguistics methods to study a born-digital cultural artifact, namely the collectible card game Hearthstone, released in 2014 and still under active development in 2020. As indicated by the developers' public statements, such a game, which is framed as an ongoing service rather than a final product, needs to strike a balance between two conflicting constraints: while the game must remain easily accessible at any stage of its development to increase the player base, the player's experience must be constantly renewed to keep the existing player base from getting bored and leaving the game. In practice, this translates into the regular addition of new card sets by the developer. Our hypothesis is that linguistic traces of these opposite forces can be found in the evolution of lexical diversity in the text of the game's rules, as opposed to its 'flavour' text, which plays no role in the game's mechanics. To test this hypothesis, a corpus documenting the first two years of the game has been built and it is distributed in open access. The analysis of lexical diversity in these data shows that the rule text vocabulary is both highly controlled and subject to steady diversification. We view these features as reflecting stakes that characterise the ongoing management and development of a game-as-a-service like Hearthstone. [ABSTRACT FROM AUTHOR]

This article presents Oralia diacrónica del español (ODE: Spanish diachronic oral corpus), a new digital resource for the study of historical dialectology. This corpus was created using TEITOK, 'a web-based framework for corpus creation, annotation, and distribution, that combines textual and linguistic annotation within a single TEI-based XML document' (Janssen, 2016 , p. 3047). ODE is a diachronic corpus of Spanish documents written between 1492 and the end of the 19th century that consists of two sub-corpora: a main corpus comprising of manuscripts from the old Kingdom of Granada (the modern-day provinces of Granada, Málaga, and Almería) and a control corpus comprising of documents from the Northern half of Spain. The texts include inventories of goods, witnesses' testimonies in criminal trials and medical certificates. The final goal is to create a corpus of approximately 600,000 tokens, especially designed for the analysis of historical dialectal research. The new online corpus has successfully overcome the following difficulties: (1) It combines a philological/textual scholarship and a corpus linguistics approach. (2) It allows working in a single edition visualised in different formats by the end user in the digital resource. (3) Furthermore, it permits independent management, since scholars can upload and edit their work, having control over their own research without the need for an external person in charge of the digital resource. [ABSTRACT FROM AUTHOR]

The digital 'Burgundian Epigraphic Corpus' is the result of a collaboration between two teams, the Corpus of Inscriptions of Medieval France (CIFM) and the Corpus of Medieval Burgundian Texts (CBMA), as part of the Cosme2 (Consortium Sources Médiévales —linked to TGIR Huma-Num from CNRS—France), dedicated to digital approaches to historical corpora. This article explains how a complex set of documents mixing Latin, Greek, and Old French texts, accompanied by rich metadata, has been processed in order to allow new surveys by humanists. It shows how the corpus is constantly reinvested and how its exploitation, thanks to digital methods, generates new data and metadata that can be reinjected into the corpus and in turn operated, creating a kind of virtuous circle. Three retro-developments are briefly discussed here: (1) semantic web, connectivity, and named entities; (2) geographic information system (GIS) and automated extraction of new metadata; (3) lemmatization and automatic language detection. [ABSTRACT FROM AUTHOR]

The daily language in mainland China has experienced a shift from traditional Chinese language to modern mandarin Chinese at the beginning of the twentieth century. The Chinese poetry 'revolution'started in the 1910s is considered as a turning point in the Chinese poetry evolution process due to the novel applications of the modern Chinese language. Many temporal poetic studies consider the poems written in traditional Chinese and modern Chinese as two different genres. The two genres are saliently different in rhyme, meter, theme, etc. We aim to detect the specific properties of the evolution process of Chinese poetry in terms of the word categories' distribution patterns. For the purpose, a corpus with 438 randomly selected traditional and modern Chinese poems is built, and some quantitative language indicators (entropy, relative entropy, repeat rate) and some exploratory statistical analysis techniques applicable in corpus linguistics and quantitative linguistics (one-way ANOVA test, cluster analysis) 1 are used to abstract and analyze language data from the corpus. It is concluded that the word categories are distributed significantly differently in traditional poetry and modern poetry. The sound reasons would be that (1) traditional Chinese poetry is more likely to focus on the application of some specific content word categories, for example, nouns, but not auxiliary words and (2) modern poems tend to choose more categories of words. From the perspective of word class distribution patterns, we suppose that the birth of modern Chinese poetry in the 1910s is a sharp change to Chinese poetry production. [ABSTRACT FROM AUTHOR]

This article presents a hybrid approach to part-of-speech tagging for undiacritized (or unvocalized) Arabic text which avoids the need for a large training set of manually tagged material. The approach is hybrid as it combines both rule-based and statistical (or data-driven) techniques. The key idea is that the training data are obtained by applying a rule-based tagger to a corpus of diacritized (or vocalized) text; a small subset of the output of the rule-based tagger is then hand-corrected, which is a much easier task than annotating it from scratch, and the results of this process are used as the training data for tagging undiacritized text. The advantage of this approach is that it requires very little manual effort. The only manual intervention is in the correction of the original training set. The accuracy obtained with this method is comparable to other state-of-the-art taggers for Arabic. [ABSTRACT FROM AUTHOR]

How has the sonnet form in Spanish evolved over the centuries? What is the distribution of metrical patterns and combinations thereof, considering diachronic, geographical, and social factors? What rhyme schemes are favoured in different periods and regions? How is enjambment distributed within the sonnet? Providing quantitative answers to such questions requires a corpus spanning several centuries, annotated for the relevant literary features and containing author metadata. The absence of appropriate digital resources to undertake a macroanalytic study of the evolution of the sonnet in Spanish led us to create the Diachronic Spanish Sonnet Corpus. This article presents how the corpus was designed for providing quantitative evidence on the evolution of sonnets in Spanish, and our findings regarding metrics and enjambment. The corpus contains 4,085 sonnets by 1,204 Spanish and Latin American authors (15th to 19th centuries), encoded in TEI, with RDFa attributes. The corpus aims at breadth, including many peripheral authors besides some major ones. Author metadata were encoded (dates, origin, gender). Scansion and enjambment were annotated automatically, with the ADSO and ANJA tools. The range of authors and periods, the use of TEI and RDFa for interoperability, and the combination of metrical and enjambment annotations goes beyond previously available digital resources. The corpus allowed us to examine the evolution of metrical patterns and their combinations after the Golden Age, complementing earlier studies. We also observed an increase in enjambment across the tercets in the 19th century, which may indicate increased variety in the discourse organization of sonnets in the period. [ABSTRACT FROM AUTHOR]

Academic writing is a complex task that requires an author to be skilled in argumentation. The goal of an academic author is to communicate ideas clearly and to convince the reader of the veracity of their claims. However, few students in lower level courses are good arguers, as this is a skill that takes time to master. With the aim of contributing to the development of this skill, we introduce a freely available annotated corpus to support research on argumentation in Spanish. To build the corpus, we developed an annotation guide to identify argumentation in paragraphs. The guide also outlines how to annotate segments of sentences as either claims or premises and how to indicate relations (support or attack) between such components. Then, an annotated corpus of 444 sections was created, and an almost perfect interannotator agreement rate was achieved for a number of its components. After its construction, the corpus was used to perform an exploratory analysis, which aimed to identify the amount of argumentation in each section as well as the patterns commonly used for argument identification. Thereafter, experiments were conducted to automatically classify argumentative components using lexical, semantic, discourse, structural, and sentiment features. A Document Occurrence Representation was also tested on the corpus constituting a novel approach in the representation of documents for automatic argument detection. The results of these experiments to automatically classify argumentative components in Spanish are very promising and seem to support the idea that linguistic feature engineering plays a crucial role in text classification. [ABSTRACT FROM AUTHOR]

This article investigates the collocational behavior of English modal auxiliaries such as may and might with the aim of finding corpus-based measures that distinguish between different modal expressions and that allow insights into why speakers may choose one over another in a given context. The analysis uses token-based semantic vector space modeling (Heylen et al. , 2015 , Monitoring polysemy. Word space models as a tool for large-scale lexical semantic analysis. Lingua, 157: 153–72; Hilpert and Correia Saavedra, 2017 , Using token-based semantic vector spaces for corpus-linguistic analyses: From practical applications to tests of theoretical claims. Corpus Linguistics and Linguistic Theory) in order to determine whether different modal auxiliaries can be distinguished in terms of their collocational profiles. The analysis further examines whether different senses of the same auxiliary exhibit divergent collocational preferences. The results indicate that near-synonymous pairs of modal expressions, such as may and might or must and have to , differ in their distributional characteristics. Also, different senses of the same modal expression, such as deontic and epistemic uses of may , can be distinguished on the basis of distributional information. We discuss these results against the background of previous empirical findings (Hilpert, 2016 , Construction Grammar and its Application to English, 2nd edn. Edinburgh: Edinburgh University Press, Flach, in press, Beyond modal idioms and modal harmony: a corpus-based analysis of gradient idiomaticity in modal-adverb collocations. English Language and Linguistics) and theoretical issues such as degrees of grammaticalization (Correia Saavedra, 2019 , Measurements of Grammaticalization: Developing a Quantitative Index for the Study of Grammatical Change. PhD Dissertation, Université de Neuchâtel) and the avoidance of synonymy (Bolinger, 1968 , Entailment and the meaning of structures. Glossa, 2 (2): 119–27). [ABSTRACT FROM AUTHOR]

Following Dr Barber's unfortunate criticism (Barber, 2018 , Marlowe and overreaching: a misuse of stylometry. Digital Scholarship in the Humanities , 34 : 1–12), in which she, with an obvious lack of familiarity with them, subjected the Rolling Delta procedures used, to the caveats of Delta and traditional stylometry, this article makes use of an extended methodological framework and applies Rolling Delta to the target texts with a totality of reference texts. The outcome is different from the expected, since the author of Tamburlaine 1 and 2 emerges as stylistically also dominant in the anonymous play The Tragedy of Locrine , in Kyd's closet play Cornelia , in Peele's The Battle of Alcazar and David and Bethsabe. In contrast, the official Marlowe corpus relates stylistically to contemporary authors, but not to the two Tamburlaines. Traditional scholarship and learning do not refute conjectures of misattributed Peele plays and there are also strong indications that plays associated with Lord Strange's Men nominally became Marlowe plays when Henslowe acquired them in 1594 for his Admiral's Men and printers made use of the cult of personality, in which the author's death became an important factor in the marketing of printed playbooks. Otherwise, there is no documentary and empirical evidence that Marlowe wrote the plays in question. The canonization of the plays occurred only in the nineteenth century, and the Marlowe we have inherited—the poet, spy, atheist, homosexual, and so on—is almost entirely an invention of the twentieth century (Hooks, 2018 , Making Marlowe. In Melnikoff, K. and Knutson, R. (eds), Christopher Marlowe, Theatrical Commerce, and the Book Trade. Cambridge: University Press, p. 98). [ABSTRACT FROM AUTHOR]

Human interaction is multimodal in nature, and meaning in discourse is created through an interplay of an array of modalities. Inspired by the integration of multimodality and corpus pragmatics, we are concerned with a general multimodal framework that facilitates the exploration on pragmatic questions by using corpus methods. By demonstrating how the study on speech acts in situated discourse is benefited from the multimodal corpus approach, we claim that the scope and methods of pragmatic studies will be enriched and the classic pragmatic theories could be further developed toward multimodal corpus pragmatics. This article, therefore, hopes to inspire further theoretical discussion and case study in this domain. [ABSTRACT FROM AUTHOR]

The extraction of large amounts of multilingual parallel text from web resources is a widely used technique in natural language processing. However, automatically collected parallel corpora usually lack precise metadata, which are crucial to accurate data analysis and interpretation. The combination of automated extraction procedures and manual metadata enrichment may help address this issue. Wikipedia is a promising candidate for the exploration of the potential of said combination of methods because it is a rich source of translations in a large number of language pairs and because its open and collaborative nature makes it possible to identify and contact the users who produce translations. This article tests to what extent translated texts automatically extracted from Wikipedia by means of neural networks can be enriched with pertinent metadata through a self-submission-based user survey. Special emphasis is placed on data usefulness, defined in terms of a catalogue of previously established assessment criteria, most prominently metadata quality. The results suggest that from a quantitative perspective, the proposed methodology is capable of capturing metadata otherwise not available. At the same time, the crowd-based collection of data and metadata may face important technical and social limitations. [ABSTRACT FROM AUTHOR]

'Democracy' is a central word of our current political lexicon, often defined as 'the power of the people'. However, in 19th century Britain, 'democracy' was not characterized by the rule of the 'people' but by the power of lower classes, of the 'populace' and the 'mob'. In political discourse, and especially in parliamentary debates, the 'people' were an antagonist of 'democracy', not its protagonist. To support these statements, this article analyses British parliamentary debates between 1775 and 1885, through both a 'distant reading' with the help of corpus linguistics tools and a closer examination of certain key debates and actors. After a brief overview of the methodology, three crucial periods of British political history are analysed. (1) The end of the 18th century, where the impact of the French Revolution on democratic vocabulary is measured. (2) The debates surrounding the 1832 Reform Act, in which the explicit differentiation between the constitutional 'people' and the democratic 'mob' is drawn out by Whigs and Tories alike. (3) The Second Reform Act (1867), also presented as a 'popular' measure, and not a step towards 'democracy'. In conclusion, the adoption of the democratic vocabulary by British Members of Parliament is traced to the 1880s, notably with the emergence of the idea of 'Tory democracy'. [ABSTRACT FROM AUTHOR]

This study examines whether a qualitative analysis of news headlines produces complementary, convergent, or dissonant findings with a quantitative analysis of the full news story. Headlines are among the most important parts of a news story and its summary. This study investigates the construction of Qaddafi in the headlines of two newspapers before and during the 2011 Libyan civil war. This is based on a sub-corpus of headlines that was taken from a 6.5-million-word corpus of two newspapers; one published in English; The Guardian , and the other in Arabic; Asharq Al-Awsat from 2009 to 2011. The analysis of the headlines has produced complementary and convergent findings with the corpus analysis and suggests that the 2011 Libyan civil war represents a turning point on how Qaddafi is represented in the investigated newspapers. This study concludes that analysing headlines proves to be a good down-sampling option to reduce large news corpora to a workable amount of data. [ABSTRACT FROM AUTHOR]

This article intends to define sensorial discourses, to discuss the way they should be analyzed by stressing the importance of corpora. Putting these thoughts into the context of the digital revolution, it will show how corpora should evolve in the digital humanities. The association of digital and sensorial discourses needs to be clarified and this article proposes a way to find new approaches to better analyze them. [ABSTRACT FROM AUTHOR]

This article describes a first attempt to annotate the full Greek papyrus corpus automatically for linguistic information. It gives an overview of existing work on Ancient Greek and analyzes the typical problems one encounters when using natural language processing techniques on (1) a historical corpus of (2) a highly inflectional language (as opposed to the more analytic present-day English) and offers solutions to them, testing several different approaches. The focus is on part-of-speech/morphological tagging and lemmatization; some syntactic parsing experiments are also briefly discussed. The conclusion discusses the strengths and shortcomings of the examined techniques and suggests possible ways to further improve tagging and parsing accuracy. [ABSTRACT FROM AUTHOR]

Vossian antonomasia is a prolific stylistic device, in use since antiquity. It can compress the introduction or description of a person or another named entity into a terse, poignant formulation and can best be explained by an example: When Norwegian world champion Magnus Carlsen is described as 'the Mozart of chess', it is Vossian antonomasia we are dealing with. The pattern is simple: A source (Mozart) is used to describe a target (Magnus Carlsen), the transfer of meaning is reached via a modifier ('of chess'). This phenomenon has been discussed before (as 'metaphorical antonomasia' or, with special focus on the source object, as 'paragons'), but no corpus-based approach has been undertaken as yet to explore its breadth and variety. We are looking into a full-text newspaper corpus (The New York Times , 1987–2007) and describe a new method for the automatic extraction of Vossian antonomasia based on Wikidata entities. Our analysis offers new insights into the occurrence of popular paragons and their distribution. [ABSTRACT FROM AUTHOR]

In this article, we introduce the first Kurdish text corpus for Central Kurdish (Sorani) branch, called AsoSoft text corpus. Kurdish language, which is spoken by more than 30 million people, has various dialects. As one of the two main branches of Kurdish, Central Kurdish is the formal dialect of Kurdish literature. AsoSoft text corpus is of size 188 million tokens and has been collected mostly from Web sites, published books, and magazines. The corpus has been normalized and converted into Text Encoding Initiative XML format. In both collecting and processing the text, we have faced several challenges and have proposed solutions to them. About 22% of the corpus is topic annotated with six topic tags, and a topic identification task has been done to evaluate the correctness of annotation. The computational experiments of the Central Kurdish text processing are also presented with the support of related supplementary statistics. For the first time, the validity of Zipf's law for Central Kurdish is presented and also perplexity of this language is calculated using standard N-gram language models. The perplexity of Central Kurdish is 276 for a tri-gram language model. [ABSTRACT FROM AUTHOR]

In this article we establish a methodological and theoretical framework for the study of large collections of visual materials. Our framework, distant viewing , is distinguished from other approaches by making explicit the interpretive nature of extracting semantic metadata from images. In other words, one must 'view' visual materials before studying them. We illustrate the need for the interpretive process of viewing by simultaneously drawing on theories of visual semiotics, photography, and computer vision. Two illustrative applications of the distant viewing framework to our own research are draw upon to explicate the potential and breadth of the approach. A study of television series shows how facial detection is used to compare the role of actors within the narrative arcs across two competing series. An analysis of the Farm Security Administration–Office of War Information corpus of documentary photography is used to establish how photographic style compared and differed amongst those photographers involved with the collection. We then aim to show how our framework engages with current methodological and theoretical conversations occurring within the digital humanities. [ABSTRACT FROM AUTHOR]

Recent research has demonstrated the potential of corpus linguistics as a solid aid in children's understanding of how language works. However, the availability of data from the UK is still somewhat limited. Most corpora are either based on a small number of schools, synchronic in nature, or focused on the post-National Curriculum era (cf. Lancaster Corpus of Children's Project Writing, the Oxford Children's Corpus, the Growth in Grammar Corpus); on the other hand, historical corpora are, unfortunately, not publicly available in electronic format (cf. the Child Language Survey or the Aspects of Writing in 16+ English Examinations, Cambridge Assessment). This article introduces the APU Writing and Reading Corpus 1979–1988, a new large electronic data set of historical materials which are linguistically annotated. The aim is two-fold. First, to describe the contents of the corpus and its compilation procedure. Second, to illustrate its potential as a research and pedagogical tool by presenting a number of research case studies and teaching materials that are currently being developed based on the corpus data. All in all, the Assessment Performance Unit (APU) Corpus contributes to both Corpus Linguistics and Educational Linguistics by presenting itself as a new resource tool with replicable methodology and objective empirical evidence, which will be of interest to academics and school teachers as well as to school material developers and policymakers. [ABSTRACT FROM AUTHOR]

Based on n text excerpts, the authorship linking task is to determine a way to link pairs of documents written by the same person together. This problem is closely related to authorship attribution questions, and its solution can be used in the author clustering task. However, no training information is provided and the solution must be unsupervised. To achieve this, various text representation strategies can be applied, such as characters, punctuation symbols, or letter n -grams as well as words, lemmas, Part-Of-Speech (POS) tags, and sequences of them. To estimate the stylistic distance (or similarity) between two text excerpts, different measures have been suggested based on the L1 norm (e.g. Manhattan, Tanimoto), the L2 norm (e.g. Matusita), the inner product (e.g. Cosine), or the entropy paradigm (e.g. Jeffrey divergence). From those possible implementations, it is not clear which text representation and distance functions produce the best performance, and this study provides an answer to this question. Three corpora, extracted from French and English literature, have been evaluated using standard methodology. Moreover, we suggest an additional performance measure called high precision (HPrec) capable of judging the quality of a ranked list of links to provide only correct answers. No systematic difference can be found between token- or lemma-based text representations. Simple POS tags do not provide an effective solution but short sequences of them form a good text representation. Letter n -grams (with n = 4–6) give high HPrec rates. As distance measures, this study found that the Tanimoto, Matusita, and Clark distance measures perform better than the often-used Cosine function. Finally, applying a pruning procedure (e.g. culling terms appearing once or twice or limiting the vocabulary to the 500 most frequent words) reduces the representation complexity and might even improve the effectiveness of the attribution scheme. [ABSTRACT FROM AUTHOR]

This article presents Parsa as an open information extraction (OIE) system for Persian. Comparing with advanced English approaches, OIE has just started to develop in other languages. Existing systems apply information about the grammar and syntactic structures of the target language to gain domain independence (which is a key goal in OIE). To improve modeling these complex structures, Parsa introduces a novel set of Patterns based on tree format. The patterns also enable Parsa to define POS tags, and lexical constraints to reduce incorrect matches. Each Tree Pattern is placed inside a Package based on its type and priority. The Packages help Parsa to alleviate some challenges in processing Persian like null-subject problem and uninformative extraction. To make the extraction process simple and coherent, we separate matching template from extraction template. An efficient algorithm for matching patterns inside dependency parse of a sentence is presented as well. Our experiments showed that Parsa achieves better performance than the state of the art systems in Persian, and highly comparable with the existing approaches in English. [ABSTRACT FROM AUTHOR]

The article presents the achievements of digital humanities in Poland, draws attention to the needs related to the development of digitization, and points to possible future undertakings aimed to popularize the accomplishments in this field. Apart from digitization, issues such as methods of sharing historic and linguistic sources in the digital form are covered. These sources include historic and scientific dictionaries of the Polish language, records, and texts dating back to before 1945. Additionally, linguistic corpora of historic Polish are presented, both those completed and those underway. The article emphasizes the imperative to create constellations of linguistic data warehouses. The last part, dedicated to the concept of the platform Diachronic Corpora of Polish, constitutes an attempt to catalog, disseminate, and made public the results of activities pertaining to works on the Polish corpora. [ABSTRACT FROM AUTHOR]

Text reuse in early Chinese transmitted texts is extensive and widespread, often reflecting complex textual histories involving repeated transcription, compilation, and editing spanning many centuries and involving the work of multiple authors and editors. In this study, a fully automated method of identifying and representing complex text reuse patterns is presented, and the results evaluated by comparison to a manually compiled reference work. The resultant data are integrated into a widely used and publicly available online database system with browse, search, and visualization functionality. These same results are then aggregated to create a model of text reuse relationships at a corpus level, revealing patterns of systematic reuse among groups of texts. Lastly, the large number of reuse instances identified make possible the analysis of frequently observed string substitutions, which are observed to be strongly indicative of partial synonymy between strings. [ABSTRACT FROM AUTHOR]