1. Text Complexity Classification Based on Linguistic Information: Application to Intelligent Tutoring of ESL

Kurdi, M. Zakaria.
The goal of this work is to build a classifier that can identify text complexity within the context of teaching reading to English as a Second Language (ESL) learners. To present language learners with texts that are suitable to their level of English, a set of features that can describe the phonological, morphological, lexical, syntactic, discursive, and psychological complexity of a given text were identified. Using a corpus of 6171 texts, which had already been classified into three different levels of difficulty by ESL experts, different experiments were conducted with five machine learning algorithms. The results showed that the adopted linguistic features provide a good overall classification performance (F-Score = 0.97). A scalability evaluation was conducted to test if such a classifier could be used within real applications, where it can be, for example, plugged into a search engine or a web-scraping module. In this evaluation, the texts in the test set are not only different from those from the training set but also of different types (ESL texts vs. children reading texts). Although the overall performance of the classifier decreased significantly (F-Score = 0.65), the confusion matrix shows that most of the classification errors are between the classes two and three (the middle-level classes) and that the system has a robust performance in categorizing texts of class one and four. This behavior can be explained by the difference in classification criteria between […]

2. Deep Learning for Period Classification of Historical Hebrew Texts

Liebeskind, Chaya ; Liebeskind, Shmuel.
In this study, we address the interesting task of classifying historical texts by their assumed period of writ-ing. This task is useful in digital humanity studies where many texts have unidentified publication dates.For years, the typical approach for temporal text classification was supervised using machine-learningalgorithms. These algorithms require careful feature engineering and considerable domain expertise todesign a feature extractor to transform the raw text into a feature vector from which the classifier couldlearn to classify any unseen valid input. Recently, deep learning has produced extremely promising re-sults for various tasks in natural language processing (NLP). The primary advantage of deep learning isthat human engineers did not design the feature layers, but the features were extrapolated from data witha general-purpose learning procedure. We investigated deep learning models for period classification ofhistorical texts. We compared three common models: paragraph vectors, convolutional neural networks (CNN) and recurrent neural networks (RNN), and conventional machine-learning methods. We demon-strate that the CNN and RNN models outperformed the paragraph vector model and the conventionalsupervised machine-learning algorithms. In addition, we constructed word embeddings for each timeperiod and analyzed semantic changes of word meanings over time.

3. Evaluating Deep Learning Methods for Word Segmentation of Scripta Continua Texts in Old French and Latin

Clérice, Thibault.
Tokenization of modern and old Western European languages seems to be fairly simple, as it stands on the presence mostly of markers such as spaces and punctuation. However, when dealing with old sources like manuscripts written in scripta continua, antiquity epigraphy or Middle Age manuscripts, (1) such markers are mostly absent, (2) spelling variation and rich morphology make dictionary based approaches difficult. Applying convolutional encoding to characters followed by linear categorization to word-boundary or in-word-sequence is shown to be effective at tokenizing such inputs. Additionally, the software is released with a simple interface for tokenizing a corpus or generating a training set.
Section: Towards a Digital Ecosystem: NLP. Corpus infrastructure. Methods for Retrieving Texts and Computing Text Similarities

4. Extracting Keywords from Open-Ended Business Survey Questions

McGillivray, Barbara ; Jenset, Gard ; Heil, Dominik.
Open-ended survey data constitute an important basis in research as well as for making business decisions. Collecting and manually analysing free-text survey data is generally more costly than collecting and analysing survey data consisting of answers to multiple-choice questions. Yet free-text data allow for new content to be expressed beyond predefined categories and are a very valuable source of new insights into people's opinions. At the same time, surveys always make ontological assumptions about the nature of the entities that are researched, and this has vital ethical consequences. Human interpretations and opinions can only be properly ascertained in their richness using textual data sources; if these sources are analyzed appropriately, the essential linguistic nature of humans and social entities is safeguarded. Natural Language Processing (NLP) offers possibilities for meeting this ethical business challenge by automating the analysis of natural language and thus allowing for insightful investigations of human judgements. We present a computational pipeline for analysing large amounts of responses to open-ended questions in surveys and extract keywords that appropriately represent people's opinions. This pipeline addresses the need to perform such tasks outside the scope of both commercial software and bespoke analysis, exceeds the performance to state-of-the-art systems, and performs this task in a transparent way that allows for scrutinising and exposing […]
Section: Project

5. A Web Application for Watermark Recognition

Bounou, Oumayma ; Monnier, Tom ; Pastrolin, Ilaria ; SHEN, Xi ; Benevent, Christine ; Limon-Bonnet, Marie-Françoise ; Bougard, François ; Aubry, Mathieu ; Smith, Marc H. ; Poncet, Olivier et al.
The study of watermarks is a key step for archivists and historians as it enables them to reveal the origin of paper. Although highly practical, automatic watermark recognition comes with many difficulties and is still considered an unsolved challenge. Nonetheless, Shen et al. [2019] recently introduced a new approach for this specific task which showed promising results. Building upon this approach, this work proposes a new public web application dedicated to automatic watermark recognition entitled Filigranes pour tous. The application not only hosts a detailed catalog of more than 17k watermarks manually collected from the French National Archives (Minutier central) or extracted from existing online resources (Briquet database), but it also enables non-specialists to identify a watermark from a simple photograph in a few seconds. Moreover, additional watermarks can easily be added by the users making the enrichment of the existing catalog possible through crowdsourcing. Our Web application is available at https://filigranes.inria.fr/.
Section: Data deluge: which skills for wich data?

6. Optical Recognition Assisted Transcription with Transkribus: The Experiment concerning Eugène Wilhelm's Personal Diary (1885-1951)

Schlagdenhauffen, Régis.
This article proposes use the Transkribus software to report on a "user experiment" in a French-speaking context. It is based on the semi-automated transcription project using the diary of the jurist Eugène Wilhelm (1866-1951). This diary presents two main challenges. The first is related to the time covered by the writing process-66 years. This leads to variations in the form of the writing, which becomes increasingly "unreadable" with time. The second challenge is related to the concomitant use of two alphabets: Roman for everyday text and Greek for private issues. After presenting the project and the specificities related to the use of the tool, the experiment presented in this contribution is structured around two aspects. Firstly, I will summarise the main obstacles encountered and the solutions provided to overcome them. Secondly, I will come back to the collaborative transcription experiment carried out with students in the classroom, presenting the difficulties observed and the solutions found to overcome them. In conclusion, I will propose an assessment of the use of this Human Text Recognition software in a French-speaking context and in a teaching situation.
Section: Digital humanities in languages

7. A Collaborative Ecosystem for Digital Coptic Studies

Schroeder, Caroline T. ; Zeldes, Amir.
Scholarship on underresourced languages bring with them a variety of challenges which make access to the full spectrum of source materials and their evaluation difficult. For Coptic in particular, large scale analyses and any kind of quantitative work become difficult due to the fragmentation of manuscripts, the highly fusional nature of an incorporational morphology, and the complications of dealing with influences from Hellenistic era Greek, among other concerns. Many of these challenges, however, can be addressed using Digital Humanities tools and standards. In this paper, we outline some of the latest developments in Coptic Scriptorium, a DH project dedicated to bringing Coptic resources online in uniform, machine readable, and openly available formats. Collaborative web-based tools create online 'virtual departments' in which scholars dispersed sparsely across the globe can collaborate, and natural language processing tools counterbalance the scarcity of trained editors by enabling machine processing of Coptic text to produce searchable, annotated corpora.