SIGUL November 2023

sigul@list.elra.info

4 participants
4 discussions

Call for participation: Shared Task on Word Embedding Evaluation for Ancient and Historical Languages (SIGTYP @ EACL)
by Oksana Dereza 10 Nov '23

10 Nov '23

Dear colleagues, [Apologies for cross-posting] In 2024, SIGTYP is hosting a *Shared Task on Word Embedding Evaluation for Ancient and Historical Languages*: https://sigtyp.github.io/st2024.html The workshop will be co-located with EACL. *Summary* In recent years, sets of downstream tasks called benchmarks have become a very popular, if not default, method to evaluate general-purpose word and sentence embeddings. Starting with decaNLP (McCann et al., 2018) and SentEval (Conneau & Kiela, 2018), multitask benchmarks for NLU keep appearing and improving every year. However, even the largest multilingual benchmarks, such as XGLUE, XTREME, XTREME-R or XTREME-UP (Hu et al., 2020; Liang et al., 2020; Ruder et al., 2021, 2023), only include modern languages. When it comes to ancient and historical languages, scholars mostly adapt/translate intrinsic evaluation datasets from modern languages or create their own diagnostic tests. We argue that there is a need for a universal evaluation benchmark for embeddings learned from ancient and historical language data and view this shared task as a proving ground for it. The shared task involves solving the following problems for 12+ ancient and historical languages that belong to 4 language families and use 6 different scripts. Participants will be invited to describe their system in a paper for the SIGTYP workshop proceedings. The task organisers will write an overview paper that describes the task and summarises the different approaches taken, and analyses their results. *Subtasks* For subtask A, participants are not allowed to use any additional data; however, they can reduce and balance provided training datasets if they see fit. For subtask B, participants are allowed to use any additional data in any language, including pre-trained embeddings and LLMs. A. Constrained 1. POS-tagging 2. Full morphological annotation 3. Lemmatisation B. Unconstrained 1. POS-tagging 2. Full morphological annotation 3. Lemmatisation 4. Filling the gaps - Word-level - Character-level *Data* For tasks 1-3, we use Universal Dependencies v. 2.12 data (Zeman et al., 2023) in 11 ancient and historical languages, complemented by 5 Old Hungarian codices from the MGTSZ website (HAS Research Institute for Linguistics, 2018) that are annotated to the same standard as the corpora available through UD. For task 4, we add historical Irish data from CELT (Ó Corráin et al., 1997), Corpas Stairiúil na Gaeilge (Acadamh Ríoga na hÉireann, 2017), and digital editions of the St. Gall glosses (Bauer et al., 2017) and the Würzburg glosses (Doyle, 2018) as a case study of how performance may vary on different historical stages of the same language. We set the upper temporal boundary to 1700 CE and do not include texts created later than this date in our dataset. List of languages: - Ancient Greek - Ancient Hebrew - Classical Chinese - Coptic - Gothic - Classical, Late & Medieval Latin - Medieval Icelandic - Old Church Slavonic - Old East Slavic - Old French - Old Hungarian - Old, Middle & Early Modern Irish - Vedic Sanskrit *Important dates* *05 Nov 2023*: Release of training and validation data *02 Jan 2024*: Release of test data *08 Jan 2024*: Submission of the systems *13 Jan 2024*: Notification of results *20 Jan 2024*: Submission of shared task papers *27 Jan 2024*: Notification of acceptance to authors *03 Feb 2024*: Camera-ready *15 Mar 2024*: Video recordings due *21/22 Mar 2024*: SIGTYP workshop *Important links* - *Registration form* <https://docs.google.com/forms/d/e/1FAIpQLSdINgMfzzZGIZ-uBVQhvyndB6yeaaj-wT7…> - Data + detailed description: https://github.com/sigtyp/ST2024 *Task organisers* - Oksana Dereza, Insight SFI Research Centre for Data Analytics, Data Science Institute, University of Galway - Priya Rani, SFI Centre for Research and Training in AI, Data Science Institute, University of Galway - Atul Kr. Ojha, Insight SFI Research Centre for Data Analytics, Data Science Institute, University of Galway - Adrian Doyle, Insight SFI Research Centre for Data Analytics, Data Science Institute, University of Galway - Pádraic Moran, School of Languages, Literatures and Cultures, Moore Institute, University of Galway - John P. McCrae, Insight SFI Research Centre for Data Analytics, Data Science Institute, University of Galway *Contact details* - Oksana: oksana.dereza(a)insight-centre.org - Priya: priya.rani(a)insight-centre.org Best wishes, Oksana and the organisers -- [image: https://nuig.insight-centre.org/] <https://www.insight-centre.org/> Oksana Dereza | PhD student on the Cardamom <http://cardamom.insight-centre.org/> project | Unit for Linguistic Data | Insight Centre for Data Analytics | Data Science Institute | University of Galway Oksana Dereza | Iarrthóir PhD ar thionscadal Cardamom <http://cardamom.insight-centre.org/> | An tAonad um Shonraí Teangeolaíocha | Insight, Ionad na hAnailísíochta Sonraí | Institiúid Eolaíochta Sonraí | Ollscoil na Gaillimhe

1 0

First Call for Papers - NeTTT’2024
by Tharindu Ranasinghe 10 Nov '23

10 Nov '23

International Conference ‘New Trends in Translation and Technology’ (NeTTT’2024) Varna, Bulgaria, 4-7 July 2024 First Call for Papers The conference The second edition of the forthcoming International Conference ‘New Trends in Translation and Technology’ (NeTTT’2024) will take place in Varna, Bulgaria, 4-7 July 2024. The objective of the conference is (i) to bridge the gap between academia and industry in the field of translation and interpreting by bringing together academics in linguistics, translation studies, machine translation and natural language processing, developers, practitioners, language service providers and vendors who work on or are interested in different aspects of technology for translation and interpreting, and (ii) to be a distinctive event for discussing the latest developments and practices. NeTTT’2024 invites all professionals who would like to learn about the new trends, present the latest work or/and share their experience in the field, and who would like to establish business and research contacts, collaborations and new ventures. The conference will take the form of presentations (peer-reviewed research and user presentations, keynote speeches), and posters; it will also feature panel discussions. The accepted papers will be published as open-access conference e-proceedings. Conference topics Contributions are invited on any topic related to latest technology and practices in machine translation, translation, subtitling, localisation and interpreting. NeTTT’2024 will feature a Special Theme Track "Future of Translation Technology in the Era of LLMs and Generative AI". The conference topics include but are not limited to: CAT tools * Translation Memory (TM) systems * NLP and MT for translation memory systems * Terminology extraction tools * Localisation tools Machine Translation * Latest developments in Neural Machine Translation * MT for under-resourced languages * MT with low computing resources * Multimodal MT * Integration of MT in TM systems * Resources for MT Technologies for MT deployment * MT evaluation techniques, metrics and evaluation results * Human evaluations of MT output * Evaluating MT in a real-world setting * Quality estimation for MT * Domain adaptation Translation Studies * Corpus-based studies applied to translation * Corpora and resources for translation * Translationese * Cognitive effort and eye-tracking experiments in translation Interpreting studies * Corpus-based studies applied to interpreting * Corpora and resources for interpreting * Interpretationese * Resources for interpreting and interpreting technology applications * Cognitive effort and eye-tracking experiments in interpreting Interpreting technology * Machine interpreting * Computer-aided interpreting * NLP for dialogue interpreting * Development of NLP based applications for communication in public service settings (healthcare, education, law, emergency services) Emerging Areas in Translation and Interpreting * MT and translation tools for literary texts and creative texts * MT for social media and real-time conversations * Sign language recognition and translation Subtitling * NLP and MT for subtitling * Latest technology for subtitling User needs * Analysis of translators’ and interpreters’ needs in terms of translation and interpreting technology * User requirements for interpreting and translation tools * Incorporating human knowledge into translation and interpreting technology * What existing translators’ (including subtitlers’) and interpreters’ tools do not offer * User requirements for electronic resources for translators and interpreters * Translation and interpreting workflows in larger organisations and the tools for translation and interpreting employed The business of translation and interpreting * Translation workflow and management * Technology adoption by translators and industry * Setting up translation /interpreting / language provider company Teaching translation and interpreting * Teaching Machine Translation * Teaching translation technology * Teaching interpreting technology * Latest AI developments in the syllabi of translation and interpreting curricula Ethical issues in translation and technology * Bias and fairness in MT * Privacy and security in cloud MT systems * Transparency and explainability of MT systems * Environmental impact on MT systems Special Theme Track - Future of Translation Technology in the Era of LLMs and Generative AI We are excited to share that NeTTT’2024 will have a special theme with the goal of stimulating discussion around Large Language Models, Generative AI and the Future of Translation and Interpreting Technology. While the new generation of Large Language Models such as CHATGPT and LLAMA showcase remarkable advancements in language generation and understanding, we find ourselves in uncharted territory when it comes to their performance on various Translation and Interpreting Technology tasks with regards to fairness, interpretability, ethics and transparency. The theme track invites studies on how LLMs perform on Translation and Interpreting Technology tasks and applications, and what this means for the future of the field. The possible topics of discussion include (but are not limited to) the following: * Changes in the translators and interpreters’ professions in the new AI era especially as a result of the latest developments in LLMSs and Generative AI * Generative AI and translation * Generative AI and interpreting * Augmenting machine translation systems with generative AI * Domain and terminology adaptation with Large Language Models * Literary translation with Large Language Models * Improving Machine Translation Quality with Contextual Prompts in Large Language Models * Prompt engineering for translation * Generative AI for professional translation * Generative AI for professional interpreting We anticipate having a special session on this theme at the conference. Submissions and publication NETTT’2024 invites the following types of submissions: User papers – for industry and practitioners. References to related work are optional. Allowed paper length: between 1 and 4 pages. Academic submissions, in three different categories (have to follow formatting requirements, references to related work are required): * (academic) full papers – describing original completed research. Allowed paper length: maximum 8 pages + 2 for references. * (academic) work-in-progress papers/posters – describing work in progress, late breaking research, papers at a more conceptual stage, and other types of papers that do not fit in the ‘full’ papers category. Allowed paper length: maximum 6 pages + 2 for references. * (academic) demo papers – describing working systems. Allowed paper length: maximum 4 pages + 2 for references. In addition to the papers, the authors will be expected to demonstrate the systems at the workshop. The submission will be electronic, using the Softconf START conference management system which will be available at the conference website soon. The follow up calls will provide more further submission details. Each submission will be reviewed by three members of the Programme Committee. The final version of the accepted papers will be published in e-proceedings with assigned ISBN and DOI. All accepted papers will be included in the conference e-proceedings which will be available at the conference. Schedule Submission deadline: 31 March 2024 Notification: 5 June 2024 Final version due: 20 June 2024 Venue The conference will take place at Conference Hotel Cherno More<https://www.chernomorebg.com/en/conference-centre.html>, Varna, situated only 200 m away from the fine sandy Black Sea beach. Further information and contact details The second call for papers is expected in December 2023 and registration will be open as from January 2024. The follow-up calls will list keynote speakers, conference chairs and members of the programme committee once confirmed. The conference website is https://nettt-conference.com and will be updated on a regular basis. For further information, please contact us at nettt2024(a)nettt-conference.com

1 0

Call for Papers and Shared Task Participation [CASE @ EACL 2024]
by Surendrabikram Thapa 06 Nov '23

06 Nov '23

Dear All, CASE 2024 will be held at EACL 2024. Call for papers: https://emw.ku.edu.tr/case-2024/ We are organizing two shared tasks. Please register and participate. We have multimodal hate speech event detection as well and it is a nice opportunity for those who could not submit last time. *Climate Activism Stance and Hate Event Detection Shared Task at CASE 2024* *Task Description: *Hate speech detection and stance detection are some of the most important aspects of event identification during climate change activism events. In the case of hate speech detection, the event is the occurrence of hate speech, the entity is the target of the hate speech, and the relationship is the connection between the two. The hate speech event has targets to which hate is directed. Identification of targets is an important task within hate speech event detection. Additionally, stance event detection is an important part of assessing the dynamics of protests and activisms for climate change. This helps to understand whether the activist movements and protests are being supported or opposed. This task will have three subtasks (i) Hate speech identification (ii) Targets of Hate Speech Identification (iii) Stance Detection. *Codalab Link: *https://codalab.lisn.upsaclay.fr/competitions/16206 *Registration: *In order to register for the shared task, please send a request in codalab. The organizers will approve requests on a daily basis. *GitHub Page: *https://github.com/therealthapa/case2024-climate *Shared task on Multimodal Hate Speech Event Detection at CASE 2024* *Task Description: *Hate speech detection is one of the most important aspects of event identification during political events like invasions. In the case of hate speech detection, the event is the occurrence of hate speech, the entity is the target of the hate speech, and the relationship is the connection between the two. Since multimodal content is widely prevalent across the internet, the detection of hate speech in text-embedded images is very important. Given a text-embedded image in the context of the Russia-Ukraine crisis, this task aims to automatically identify hate speech and its targets. This task will have two subtasks (i) Hate speech identification (ii) Targets of Hate Speech Identification. *Codalab Link: *https://codalab.lisn.upsaclay.fr/competitions/16203 *Codalab Link to Multimodal Hate Speech Event Detection Shared Task at CASE 2023:* https://codalab.lisn.upsaclay.fr/competitions/13087 *Registration: *In order to register for the shared task, please send a request in codalab. The organizers will approve requests on a daily basis. *GitHub Page: *https://github.com/therealthapa/case2024-multimodal-hate Best Regards, Surendrabikram Thapa Research Faculty Virginia Tech, USA

1 0

SIGUL2023 Proceedings now available on the ISCA Archive
by Claudia Soria 02 Nov '23

02 Nov '23

Dear Members of the SIGUL list, we are happy to announce that the proceedings of the SIGUL 2023 Workshop in Dublin are now available on the ISCA archive. https://doi.org/10.21437/SIGUL.2023 All the best Claudia Soria, Maite Melero, Sakriani Sakti -- Ricercatrice Istituto di Linguistica Computazionale "A. Zampolli" Consiglio Nazionale delle Ricerche Pisa -- Researcher "A. Zampolli" Institute for Computational Linguistics National Research Council Pisa, Italy

1 0

2024

2023

2022

2021

2020

2019

2018

2017

SIGUL November 2023