Call for Abstracts. AUTOMATED TEXTS IN THE ROMANCE LANGUAGES

TAPA, 2023

This paper argues that machine learning (ML) has a role to play in the future of philology, understood here as a discipline concerned with preserving and elucidating the global archive of premodern texts. We offer one initialcase study in order to outline broader possibilities for the field. The argument is in four parts. First, we offer a brief introduction to the history of classical philology, focusing on the development of three technologies: writing, printing, and digitizing. We evaluate their impact and emphasize some elements of continuity in philological practice. Second, we describe Logion, an ML model we are currently developing to support various philological tasks, such as making conjectures to fill lacunae, identifying scribal errors, and proposing emendations.In part three, we present some of the results achieved to date in editing the work of the Byzantine author Michael Psellos. Finally, we build on the specific study presented (part three), as well as our more general considerations on philology (part one) and ML (part two), in order to shed light on current challenges and future opportunities for the global archive of premodern texts.

Machine Translation Summit 2019, 2019

The question of translation quality and how to define and measure it is one that has occupied a central position in both translation studies (TS) and machine translation (MT) since their respective geneses. TS has largely turned away from questions of absolute quality in recent years, towards a pluralistic notion that any translation produced by a human is a genuine reflection of that human’s interpretation of the source text. With this reasoning in mind and lacking any generally agreed standard by which to judge translations, ascribing absolute or relative quality to such translations would be self-contradictory (Drugan 2013: 45). MT, however, cannot adopt the same stance with reference to its own outputs, since they are not the direct products of human interpretations, and so, can simply be inadequate or unacceptable to target readers. Nonetheless, a definable ideal of translation quality remains elusive (Way 2013). As MT systems have developed, their use by professional translators and by end users bypassing human translators altogether has become more and more an accepted practice. However, this acceptance is only applicable to certain domains of texts. Literature has historically been held up as one domain in which machine translation and computer aided translation (CAT) are both of little or no use (Alcina 2008: 95). The aim of this workshop is to ask whether literature really is off-limits to technology. Of the twelve abstract submissions received for this workshop, ten (83.3%) were accepted for presentation after peer review by the workshop’s Organizing Committee. Of these ten, six presenters opted also to formulate full articles, which are published in these proceedings. Of those which did not opt for full publication, only abstracts are reproduced here. The submissions are vary widely in terms of language pairs, with as many as thirteen languages: Catalan, Dutch, English, German, Greek, Irish, Polish, Portuguese, Russian, Scottish Gaelic, Slovene, Spanish, and Turkish, analyzed from a variety of angles and taking in different issues as they pertain to the qualities of literary translations produced wholly or partly by machines. For the full proceedings of the workshop, please visit: https://www.aclweb.org/anthology/volumes/W19-73/

Hipogrifo. Revista de literatura y cultura del Siglo de Oro, 2023

This is a translation of the article "La Inteligencia Artificial al rescate del Siglo de Oro: transcripción y modernización automática de mil trescientos impresos y manuscritos teatrales". https://www.revistahipogrifo.com/index.php/hipogrifo/article/view/1262 https://doi.org/10.13035/H.2023.11.01.08 Cuéllar, Álvaro. (2023). «La Inteligencia Artificial al rescate del Siglo de Oro. Transcripción y modernización automática de mil trescientos impresos y manuscritos teatrales», Hipogrifo. Revista de literatura y cultura del Siglo de Oro, vol. 11, núm. 1, pp. 101-115, https://doi.org/10.13035/H.2023.11.01.08. A high percentage of theatrical prints and manuscripts from the aurisecular period have never been transcribed in an analogical or, of course, digital format. It is therefore impossible to use these documents to carry out searches of our interest or for the valuable computer analyses (stylometry, topic modelling, sentiment analysis, etc.) that have been developed in recent years. Thanks to Artificial Intelligence (Transkribus) and HTR (Handwritten Text Recognition) techniques, I have trained three models, already public for the research community, capable of transcribing and orthographically modernizing these documents automatically with a high degree of precision: around 97% of success in prints and 91% in manuscripts. Through these models I have been able to process some 1,300 theatrical plays contained in prints and manuscripts from numerous libraries, archives, and other digitized sources. The resulting transcripts are now part of the ETSO project, of the TEXORO search engine and, in addition to being an advanced starting point for careful editing of the texts, they themselves have sufficient quality to be subjected to stylometric analysis, which is yielding authorship attributions of interest.

2015

Welcome to the 4 th edition of the Workshop on Computational Linguistics for Literature. After the rounds in Montréal, Atlanta and Göteborg, we are pleased to see both the familiar and the new faces in Denver. We are eager to hear what our invited speakers will tell us. Nick Montfort, a poet and a pioneer of digital arts and poetry, will open the day with a talk on the use of programming to foster exploration and fresh insights in the humanities. He suggests a new paradigm useful for people with little or no programming experience. Matthew Jockers's work on macro-analysis of literature is well known and widely cited. He has published extensively on using digital analysis to view literature diachronically. Matthew will talk about his recent work on modelling the shape of stories via sentiment analysis. This year's workshop will feature six regular talks and eight posters. If our past experience is any indication, we can expect a lively poster session. The topics of the 14 accepted papers are diverse and exciting. Once again, there is a lot of interest in the computational analysis of poetry. Rodolfo Delmonte will present and demo SPARSAR, a system which analyzes and visualizes poems. Borja Navarro-Colorado will talk about his work on analyzing shape and meaning in the 16 th and 17 th century Spanish sonnets. Nina McCurdy, Vivek Srikumar & Miriah Meyer propose a formalism for analyzing sonic devices in poetry and describe an open-source implementation. This year's workshop will witness a lot of work on parallel texts and on machine translation of literary data. Laurent Besacier & Lane Schwartz describe preliminary experiments with MT for the translation of literature. In a similar vein, Antonio Toral & Andy Way explore MT on literary data but between related languages. Fabienne Cap, Ina Rösiger & Jonas Kuhn explore how parallel editions of the same work can be used for literary analysis. Olga Scrivner & Sandra Kübler also look at parallel editionsin dealing with historical texts. Several other papers cover various aspects of literary analysis through computation. Prashant Jayannavar, Apoorv Agarwal, Melody Ju & Owen Rambow consider social network analysis for the validation of literary theories. Andreas van Cranenburgh & Corina Koolen investigate what distinguishes literary novels from less literary ones. Dimitrios Kokkinakis, Ann Ighe & Mats Malm use computational analysis and leverage literature as a historical corpus in order to study typical vocations of women in the 19 th century Sweden. Markus Krug, Frank Puppe, Fotis Jannidis, Luisa Macharowsky, Isabella Reger & Lukas Weimar describe a coreference resolution system designed specifically with fiction in mind. Stefan Evert, Thomas Proisl, Thorsten Vitt, Christof Schöch, Fotis Jannidis & Steffen Pielström explain the success of Burrows's Delta in literary authorship attribution. Last but not least, there are papers which do not fit into any other bucket. Marie Dubremetz & Joakim Nivre will tell us about automatic detection of a rare but elegant rhetorical device called chiasmus. Julian Brooke, Adam Hammond & Graeme Hirst describe a tool much needed in the community: GutenTag, a system for accessing Project Gutenberg as a corpus. iii To be sure, there will be much to listen to, learn from and discuss for everybody with the slightest interest in either NLP or literature. We cannot wait for June 4 (-:). This workshop would not have been possible without the hard work of our program committee. Many people on the PC have been with us from the beginning. Everyone offers in-depth, knowledgeable advice to both the authors and the organizers. Many thanks to you all! We would also like to acknowledge the generous support of the National Science Foundation (grant No. 1523285), which has allowed us to invite such interesting speakers.

Proceedings of Digital Humanities Conference, 14.07.2023, Graz, Austria, 2023, 110–111, 2023

AI-supported indexing of handwritten dialect lexis: The pilot study "DWA Austria" as a case study.

East-West Cultural Passage, 2023

If you translate long into the machine, the machine translates back into you," is one of the issues the present article strives to establish and explore qualitatively. I intend to examine the effectiveness and efficiency of machine-assisted translations of significant literary works from a hermeneutical perspective. Essentially, I analyse the output of automated translation platforms such as Google Translate and compare them to human translation. This investigation is valuable in determining whether translators should exercise caution when utilizing translation platforms for culturally rich literary works. Additionally, the article scrutinizes the localisation, cultural, and grammatical coherence of Homer's The Iliad translated from English to Romanian using the Google Translate platform. The human translations used are rendered into English and Romanian from Greek. As Homer's Greek remains incomprehensible to the translation platform, we employ a secondary translation technique for a tertiary machine-assisted output. Nonetheless, this approach highlights the serious pitfalls of using translation platforms haphazardly in translation work. This analysis will show how awareness of the machine's imperfect translation capabilities may, in turn, enhance the human translator's awareness of what works while translating with the help of an online translation tool.

EVALITA Evaluation of NLP and Speech Tools for Italian - December 17th, 2020, 2020

English. This paper describes Il mago della Ghigliottina, a bot which took part in the Ghigliottin-AI task of the Evalita 2020 evaluation campaign. The aim is to build a system able to solve the TV game "La Ghigliottina". Our system has already participated in the Evalita 2018 task NLP4FUN. Compared to that occasion, it improved its accuracy from 61% to 68.6%. Italiano. Questo contributo descrive Il mago della Ghigliottina, un bot che ha partecipato a Ghigliottin-AI, uno dei task di Evalita 2020. Scopo del task è mettere in piedi un sistema automatico capace di risolvere il gioco televisivo "La Ghigliottina". Il nostro sistema ha già partecipato all'edizione del 2018 di Evalita al task NLP4FUN. Rispetto all'edizione del 2018 di NLP4FUN, l'accuratezza è salita dal 61% al 68.6%. 1 Introduction In this paper we describe Il mago della ghigliottina (Sangati et al., 2020), a bot which participated in Ghigliottin-AI, one of the Evalita 2020 tasks (Basile et al., 2020a). Evalita 1 (Basile et al., 2020b) is an initiative of AILC (Associazione Italiana di Linguistica Computazionale) and is a periodic evaluation campaign of Natural Language Processing (NLP) and speech tools for the Italian language, which takes place every two years in conjunction with CLiC-IT 2 , the Italian Conference on Computational Linguistics. Ghigliottin-AI takes its cue from the Evalita 2018 NLP4FUN

2024

On behalf of the Conveners, it is my great pleasure to invite all interested colleagues—especially philologists & those researching the interrelationship between artificial intelligence and literature—to participate in the 1st International Scientific Symposium “The Languages of Contemporary Literature Studies”; details are in the attachment below ↓ The Registration Form: https://docs.google.com/document/d/10OyVHIdBZm7054Uu4y_l0YVa9Xu3snJ7

Journal of French Language Studies, 1993

there is little to be gained from such an examination' (p. 30). In short, the functional analysis ofliterary texts is potentially valuable and illuminating because it is objective and rigorous, but actually carrying its logic through to the bitter end is-entre nous-a bit of a bore. Nevertheless, as a practical introduction to the discipline ofliterary stylistics and, equally significantly, as a manual in the Richards tradition on 'how to read a page', The Literary Stylistics of French is a very serviceable book indeed. Students will immediately recognise and appreciate that here, for once, is a sensible, thorough and 'user-friendly' explanation of an otherwise rebarbative subject. It is unfortunate that having concentrated throughout on 'literary' text, the author should have felt obliged to choose non-literary examples as the objects of'summary analyses'. This switch in focus is inconsistent with her approach and has left virtually untouched the difficult but central relationship between linguistics and semiotics which the inclusion of non-literary texts would normally imply. Also, some of the French examples created by the author to illustrate a point of style, for instance those relating to anaphoric reference (p. 43), might better have been chosen from authentic literary texts. Finally, and much more importantly than the occasional typographical errors, some might take issue with the author's assertion (following Cressot) that 'the evaluation of textual quality is purely the territory of literary studies' (p. 148). What about non-literary texts? Surely the ultimate justification for stylistic analysis, and for the extension of stylistics to the realm of semiotics, is precisely that it informs judgements of aesthetic value and social significance. If stylistics does not fulfil this role, it is indeed little more than a mechanistic tool for exemplifying current linguistic theories or describing readers' behaviour, one which would rightly justify an apology rather than the note of unabashed jouissance on which Carol Bellard-Thomson ends her book.