LChange'24 is the fifth workshop for computational approaches to historical language change with the focus on digital text corpora. Come join us for this exciting adventure!
The workshop builds upon its first iteration in 2019, and the subsequent events (2021, 2022, 2023). It will be colocated with ACL 2024 in Bangkok (Thailand), as a hybrid event. The workshop will take place on Thursday 15 August 2024.
Proceedings are available here.
Start-End | Titel | Author(s) | Link(s) |
---|---|---|---|
9.15-9.30 | INTRODUCTION | ||
9.30-10.30 | KEYNOTE 1, Moderator: Nina Tahmasebi | Antske Fokkens | |
10.30-11.00 | COFFEE BREAK | ||
SESSION 1 Chair: Francesco Periti | |||
11.00-11.20 | A Semantic Distance Metric Learning approach for Lexical Semantic Change Detection | Taichi Aida, Danushka Bollegala | slides |
11.20-11.40 | Towards a GoldenHymns Dataset for Studying Diachronic Trends in 19th Century Danish Religious Hymns | Ea Lindhardt Overgaard, Pascale Feldkamp, Yuri Bizzoni | slides |
11.40-12.00 | Definition generation for lexical semantic change detection | Mariia Fedorova, Andrey Kutuzov, Yves Scherrer | slides |
12.00-13.00 | LUNCH BREAK | ||
13.00-13.45 | KEYNOTE 2, Moderator: Andrey Kutuzov | Johann-Mattis List | |
SESSION 2 Chair: Pierluigi Cassotti | |||
13.45-14.05 | Towards an Onomasiological Study of Lexical Semantic Change Through the Induction of Concepts | Bastien Liétard, Mikaela Keller, Pascal Denis | slides |
14.05-14.25 | Towards a Complete Solution to Lexical Semantic Change: an Extension to Multiple Time Periods and Diachronic Word Sense Induction | Francesco Periti, Nina Tahmasebi | slides |
14.25-14.45 | AXOLOTL’24 Shared Task on Multilingual Explainable Semantic Change Modeling | Mariia Fedorova, Timothee Mickus, Niko Tapio Partanen, Janine Siewert, Elena Spaziani, Andrey Kutuzov | slides |
SESSION POSTER PITCH Chair: Pierluigi Cassotti | |||
15.30-16.30 | POSTER SESSION | ||
16.30-17.30 | Round Table, Moderator: Andrey Kutuzov | ||
17.30-17.45 | CLOSING REMARKS |
Poster presentations:
This year we are happy to welcome Antske Fokkens and Johann-Mattis List as keynote speakers.
Antske Fokkens (Computational Linguistics & Text Mining Lab, Vrije Universiteit Amsterdam - Algorithms, Geometry & Applications, Eindhoven University of Technology)
Title of talk: What Changes in Language Modeling mean for Modeling Language Change
Language change detection has emerged as a subdomain that has caught the interest (computational) linguistics, historians, social scientists and computer scientists. Despite this enthusiasm and stable attention from the NLP community over multiple years, our methods keep on having difficulties in distinguishing valid signals of change from noise. This holds both for methods using static word embeddings as well as for more recent explorations with methods that make use of contextual embeddings. The question of how to distinguish true signal from noise has received substantial attention from the field, with the design of benchmarks, control tests and artificially created samples and data. An aspect that has, to my knowledge, received less attention is the fundamental differences between most methods using static on the one hand, and most methods using contextualized embeddings on the other hand. Mainly, methods that make use of static embeddings involve creating new embeddings for the full vocabular creating general shifts in space. Methods using contextualized embeddings on the other hand mostly make use of pretrained language models, either as is or with some continual training on the target corpus. Change is then studied by comparing instances including target terms from different corpora. In this talk, I will explore what these fundamental differences mean when carrying out methodological checks and balances for studying language change with the aim of answering the question: how can we find meaningful change and know that is meaningful.
Johann-Mattis List (Chair of Multilingual Computational Linguistics, University of Passau)
Title of talk: New Approaches in Computer-Assisted Language Comparison
The field of computer-assisted language comparison seeks to develop interactive computational workflows that facilitate those tasks that linguists working in the field of historical or typological language comparison usually carry out manually. While the field has substantially grown over the past decade, with new tools and new workflows that support computer-assisted analyses, there remain many challenges that have so far not yet been addressed in computer-assisted approaches. In this study, three new approaches that facilitate detailed comparative analysis will be presented. The first approach allows for an efficient manual labeling of correspondence patterns in comparative wordlists, the second approach allows to group sounds in phonetically transcribed wordlists and to segment words into morphemes. The third approach allows to correct individual word forms in comparative wordlists, by contrasting the reflexes of a proto-form that one would expect under the assumption of regular sound change with the reflexes that are attested in the data. All approaches are implemented in an interactive web-based tool that is freely available and integrated with previous computer-assisted tools and workflows.
We hope to make this fifth edition another resounding success!
The main topic of the workshop remains the same: all aspects around computational approaches to historical language change with the focus on digital text corpora. LChange'19 resulted in a book on Computational approaches to semantic change.
This workshop explores state-of-the-art computational methodologies, theories and digital text resources on exploring the time-varying nature of human language.
The aim of this workshop is three-fold. First, we want to provide pioneering researchers who work on computational methods, evaluation, and large-scale modelling of language change an outlet for disseminating cutting-edge research on topics concerning language change. We want to utilize this workshop as a platform for sharing state-of-the-art research progress in this fundamental domain of natural language research.
Second, in doing so we want to bring together domain experts across disciplines by connecting researchers in historical linguistics with those that develop and test computational methods for detecting semantic change and laws of semantic change; and those that need knowledge (of the occurrence and shape) of language change, for example, in digital humanities and computational social sciences where text mining is applied to diachronic corpora subject to e.g., lexical semantic change.
Third, the detection and modelling of language change using diachronic text and text mining raise fundamental theoretical and methodological challenges for future research.
Besides these goals, this workshop will also support discussion on the evaluation of computational methodologies for uncovering language change. SemEval2020 Task1 on unsupervised detection of lexical semantic change attracted three figure submission numbers and a total of 21 submitted system papers. Since then, three more tasks have been completed in Italian, Russian, and Spanish.
We invite original research papers from a wide range of topics, including but not limited to:
URL for submissions: https://openreview.net/group?id=aclweb.org/ACL/2024/Workshop/LChange.
We accept two types of submissions, long and short papers, following the ACL 2024 style (see eg the Overleaf template), and the ACL submission policy.
Long and short papers may consist of up to eight (8) and four (4) pages of content, respectively, plus unlimited references; final versions will be given one additional page of content so that reviewers' comments can be taken into account.
LChange’24 also welcomes papers focusing on releasing a dataset or a model; these papers fall into the short paper category. To encourage model and dataset sharing at the reviewing phase, model and dataset papers do not need to be anonymous.
Accepted papers will be presented orally or as posters and included in the workshop proceedings. Submissions are open to all, and are to be submitted anonymously. All papers will be refereed through a double-blind peer review process by at least three reviewers with final acceptance decisions made by the workshop organizers.
This year, and echoing LChange 22 in Dublin, we are happy to host a shared task within LChange: the AXOLOTL-24 Shared Task on Explainable Semantic Change Modeling. AXOLOTL-24 stands for “Ascertain and eXplain Overhauls of the Lexicon Over Time at LChange'24” and is organised by Mariia Fedorova and Andrey Kutuzov (University of Oslo), Timothee Mickus, Niko Partanen and Janine Siewert (University of Helsinki), and Elena Spaziani (Sapienza University Rome).
The shared task presents two subtasks:
More information, including timeline and instructions, is available on https://github.com/ltgoslo/axolotl24_shared_task/.
If you have published in the field previously, and are inrerested in helping out in the PC to review papers, send us an email.
Organisers: Nina Tahmasebi, Syrielle Montariol, Andrey Kutuzov, David Alfter, Francesco Periti , and Pierluigi Cassotti.