Contact: firstname.lastname@example.orgThe purpose of the workshop is 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 Papers will be on substantial, original, and unpublished research on these topics, potentially including strong work in progress.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
- Models of psycholinguistic experiments
- Morpheme identification and word segmentation
- Algorithms, including finite-state methods
- Corpus linguistics
- Machine transliteration and back-transliteration
- Speech technologies relating to phonetics or phonology
- Speech science (both production and comprehension)
- Analysis or exploitation of multilingual, multi-dialectal, or diachronic data
- Instructional technologies for second-language learners
- Integration of morphology, phonology, or phonetics with other NLP tasks
- Tools and resources
- Approaches to orthographic variation
One of the missions of SIGMORPHON is to encourage 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 2017. 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.
- ? May 2017 Paper submission deadline
- ? June 2017: Notification of acceptance
- ? June 2017: Camera-ready papers due
- ??? 2017: Workshop
Content: Long papers should be original, topical, and clear. Completed work is preferable to intended work, but in any event the paper should clearly indicate the state of completion of the reported results. We also encourage short submissions, which can cover research, or can 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. One additional page is allowed for the References section in both cases. However, all material other than the bibliography must fall within the first 8/4 pages! We strongly recommend the use of the LaTeX style files or Microsoft Word document template that will available on the ACL conference web site. We reserve the right to reject submissions that do not conform to these styles, including font size restrictions.
Online submission is not yet available
- Mans Hulden, University of Colorado
- Sandra Kuebler, Indiana University
Email address to contact workshop organizers: email@example.com
Shared Task: Universal Morphological Reinflection
More news later!
Morphological analysis and generation of previously unseen word forms is a fundamental problem in NLP the accuracy of which is crucial for the success of many downstream tasks. Learning morphological inflection patterns from labeled data is a current challenge that is addressed by a number of papers published in various ACL-related venues. To bring together researchers working on inference problems related to morphology, SIGMORPHON is planning a shared task in concjuntion with the workshop.
In the shared task, participants will build systems that can learn to solve different reinflection problems using labeled data. An example of English reinflection is the conversion of "ran" to its present participle, "running". Specifically, a participant system needs to be able to (1) produce inflected word forms from a lemma, and (2) generate a specific inflected word form from some other labeled inflected form, and (3) generate inflected word forms from unlabeled word forms of the same lemma. All submitted systems will be compared on a held-out test set.
Participants will also be invited to describe their system in a short paper for the SIGMORPHON 2017 workshop. The task organizers will write an overview paper with descriptions and summaries of the different approaches taken and their results.
Shared Task: Organizers
- Ryan Cotterell (Johns Hopkins University)
- John Sylak-Glassman (Johns Hopkins University)
- Christo Kirov (Johns Hopkins University)
- Géraldine Walther (The University of Zurich)
- Manaal Faruqui (Google)
- Sandra Kübler (Indiana University)
- David Yarowsky (Johns Hopkins University)
- Jason Eisner (Johns Hopkins University)
- Mans Hulden (University of Colorado)