SIGMORPHON 2023 will be co-located with ACL 2023 in Toronto, Canada.
SIGMORPHON aims to bring together researchers interested in applying computational techniques to problems in morphology, phonology, and phonetics. Work that addresses orthographic issues is also welcome. Papers will be on substantial, original, and unpublished research on these topics, potentially including strong work in progress. Appropriate topics include (but are not limited to) the following as they relate to the areas of the workshop:
- New formalisms, computational treatments, or probabilistic models of existing linguistic formalisms
- Unsupervised, semi-supervised, or machine learning of linguistic knowledge
- Analysis or exploitation of multilingual, multi-dialectal, or diachronic data
- Integration of morphology, phonology, or phonetics with other NLP tasks
- Algorithms for string analysis and manipulation, including finite-state methods
- Models of psycholinguistic experiments
- Approaches to orthographic variation
- Approaches to morphological reinflection
- Corpus linguistics
- Machine transliteration and back-transliteration
- Morpheme identification and word segmentation
- Speech technologies relating to phonetics or phonology
- Speech science (both production and comprehension)
- Instructional technologies for second-language learners
- Tools and resources
SIGMORPHON encourages interaction between work in computational linguistics and work in theoretical phonetics, phonology and morphology, and to ensure that each of these fields profits from the interaction. Our recent meetings have been successful in this regard, and we hope to see this continue in 2023.
Many mainstream linguists studying phonetics, phonology and morphology are employing computational tools and models that are of considerable interest to computational linguists. Similarly, models and tools developed by and for computational linguists may be of interest to theoretical linguists working in these areas. This workshop provides a forum for these researchers to interact and become exposed to each others’ ideas and research.
Important Dates
Tentative schedule
January 18, 2023: First Call for Workshop Papers
April 1529, 2023: Workshop Paper Due Date
May 2224, 2023: Notification of acceptance
May 30June 3, 2023: Camera-Ready papers due
June 12, 2023: Pre-recorded video due
July 14, 2023: Workshop Date
Paper submission
Content
Long papers should be original, topical, and clear. Completed work is preferable to intended work. Either way, the paper must disclose the state of completion of the reported results. We also encourage short submissions. These can either cover research or describe important problems (new or old).
Submission format
The only accepted format for submitted papers is Adobe PDF. Submissions should be anonymous, without authors or an acknowledgement section; self-citations should appear in third person. Submissions should follow the two-column format of ACL proceedings, and long papers should not exceed eight (8) pages, short papers should not exceed four (4) pages. Unlimited additional pages are allowed for the references section in both cases. However, all material other than the bibliography must fall within the first 8/4 pages! The camera-ready submission will be allowed to have 1 extra page to address reviewer concerns. We encourage the submission of supplemental material such as data and code, as well as appendices; however, supplemental material should not be essential for the understanding of the submission. We strongly recommend the use of the LaTeX style files or Microsoft Word document template on the ACL conference website. We reserve the right to reject submissions that do not conform to these styles, including font size restrictions.
Anonymity period
SIGMORPHON 2023 adopts ACL’s new policies for submission, review, and citation. Submissions that violate any of these policies will be rejected without review. Most importantly, the policies refer to the anonymity period, which begins one month before the 2022 submission deadline and ends at time of notification (or withdrawal).
Program
We have a very full program scheduled for July 14.
Invited Talks
SIGMORPHON is pleased to welcome the following invited speakers to our workshop.
Kyle Gorman - Graduate Center, City University of New York
“Features in Computational Phonology”
The linguist Ray Jackendoff considers “the discovery of distinctive features…to be a scientific achievement on the order of the discovery and verification of the periodic table in chemistry.” Despite this, quite a bit of work in phonology—whether formal or computational—works with extensional sets of indivisible segments rather than the intensional, internally-structured definitions derived from distinctive features. In this talk I will first present philosophical and empirical arguments that phonological patterns are defined intensionally: segments are bundles of features and processes are defined in terms of “natural classes”, or conjunctions of feature specifications. Then, I will argue against the received wisdom—both in formal and computational phonology—that phonological patterns should be specified “minimally”, in terms of the fewest possible features consistent with the observed data. I show that feature minimization has undesirable cognitive and computational properties. In contrast, feature maximization—which, under the intensional view, is equivalent to set intersection—is empirically adequate and free of the problems that plague feature minimization.
Kyle Gorman is a professor of linguistics at the Graduate Center, City University of New York, and director of the master’s program in computational linguistics. He is also a software engineer at Google LLC. Along with his collaborators, he is the author of Finite-State Text Processing and of award-winning papers at ACL 2019 and WNUT 6.
Carmen Saldana - University of Zürich
“Cross-linguistic recurrent patterns in morphology mirror human cognition”
A foundational goal of language science is to detect and define the set of constraints that explain cross-linguistic recurrent patterns (i.e., typological universals) in terms of fundamental shared features of human cognition. In this talk, I will present a series of Artificial Language Learning experimental studies which test a hypothesised link between biases in language learning and morphological universals in typology both at the syntagmatic (i.e., morpheme order) and paradigmatic levels (e.g., structure of inflectional paradigms). I will focus in particular on two types of universals in inflectional morphology: (1) affixes with stronger structural relationships to the word stem tend to appear linearly closer to it, and (2) different categories with the same identity (be it the same word form, or the same word structure) in morphological paradigms tend to be semantically similar. The results from the studies I will present provide evidence in favour of a shared typological and learning bias towards compositional transparency and locality in morpheme order, and a bias towards partitions of morphological paradigms that reflect semantic relatedness. In light of these results, I will argue that cross-linguistic recurrent morphological patterns mirror to some extend universal features of human cognition.
Carmen Saldana is currently a postdoctoral fellow in the Department of Comparative Language Science at the University of Zurich. Her research focuses on investigating the cognitive biases and processes that shape the current cross-linguistic distributions of morphosyntactic features and their evolution. Her work specifically contributes to the understanding of the relationship between individuals’ cognitive biases at play during language learning and use and universal tendencies in morpheme order and paradigmatic morphological structure. She carries out her research within a comprehensive interdisciplinary framework combining methods from linguistic theory, quantitative typology and experimental linguistics.
Shared Tasks
SIGMORPHON is hosting 2 shared tasks this year. Please visit the respective pages for more information.
Inflectional Morphology
Automatic Glossing
Program Committee
Khuyagbaatar Batsuren, National University of Mongolia
Gasper Begus, University of California, Berkeley
Canaan Breiss, MIT
Basilio Calderone, CNRS
Daniel Dakota, Indiana University
Aniello De Santo, University of Utah
Indranil Dutta, Jadavpur University
Jason Eisner, Johns Hopkins University
Micha Elsner, The Ohio State University
Omer Goldman, Bar Ilan University
Nizar Habash, NYU Abu Dhabi
Nabil Hathout, CNRS
Mathilde Hutin, Computer Sciences Laboratory for Mechanics and Engineering Sciences
Cassandra Jacobs, University of Buffalo
Adam Jardine, Rutgers University
Jordan Kodner, Stony Brook University
Sandra Kübler, Indiana University
Giorgio Magri, CNRS
Rob Malouf, San Diego State University
Connor Mayer, University of California, Irvine
Kemal Oflazer, CMU Qatar
Jeff Parker, Brigham Young University
Jelena Prokic, Universiteit Leiden
Jonathan Rawski, San Jose State University
Brian Roark, Google AI
Eric Rosen, University of British Columbia
Maria Ryskina, MIT
Miikka Silfverberg, University of British Columbia
Kairit Sirts, University of Tartu
Caitlin Smith, UC Davis
Morgan Sonderegger, McGill University
Kenneth Steimel, Indiana University
Ekaterina Vylomova, University of Melbourne
Adam Wiemerslage, University of Colorado
Adina Williams, Facebook AI Research
Colin Wilson, Johns Hopkins University
Changbing Yang, University of British Columbia
Kristine Yu, University of Massachusetts, Amherst
Organizers
- Garrett Nicolai, University of British Columbia
- Eleanor Chodroff, University of York
- Çağrı Çöltekin, University of Tübingen
- Fred Mailhot, Dialpad, Inc.