Contact: sigmorphon2016@gmail.com
The 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 Papers will be on substantial, original, and unpublished research on these topics, potentially including strong work in progress.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 2014. 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
8 May 2016EXTENDED 15 May 2016, 23:59 EDT: Paper submission deadline- 5 June 2016: Notification of acceptance
- 22 June 2016: Camera-ready papers due
- 11 August 2016: Workshop
Schedule
The full workshop schedule, including accepted papers for the shared task track! We look forward to seeing you in Berlin.
Session 1: Phonetics
- 9:00: Mining linguistic tone patterns with symbolic representation: Shuo Zhang
Invited Talk
- 9:30: Beyond bigrams for surface-based phonotactic models: a case study of South Bolivian Quechua: Colin Wilson, Johns Hopkins University (joint work with Gillian Gallagher)
Coffee break, 10:30-11:00
Session 2: Shared task: Morphological Reinflection
- 11:00: Shared task overview and results: Ryan Cotterell and Mans Hulden
- 11:30: Shared task poster session
Shared task posters:
- Morphological reinflection with convolutional neural networks: Robert Östling
- EHU at the SIGMORPHON 2016 Shared Task. A Simple Proposal: Grapheme-to-Phoneme for Inflection: Iñaki Alegria and Izaskun Etxeberria
- Morphological Reinflection via Discriminative String Transduction: Garrett Nicolai, Bradley Hauer, Adam St Arnaud and Grzegorz Kondrak
- Morphological reinflection with conditional random fields and unsupervised features: Ling Liu and Lingshuang Jack Mao
- Improving Sequence to Sequence Learning for Morphological Inflection Generation: The BIU-MIT Systems for the SIGMORPHON 2016 Shared Task for Morphological Reinflection: Roee Aharoni, Yoav Goldberg and Yonatan Belinkov
- Evaluating Sequence Alignment for Learning Inflectional Morphology: David King
- Using longest common subsequence and character models to predict word forms: Alexey Sorokin
- MED: The LMU System for the SIGMORPHON 2016 Shared Task on Morphological Reinflection: Katharina Kann and Hinrich Schütze
- The Columbia University - New York University Abu Dhabi SIGMORPHON 2016 Morphological Reinflection Shared Task Submission: Dima Taji, Ramy Eskander, Nizar Habash and Owen Rambow
Lunch: 12:00-14:00
Session 3: Workshop posters, 14:00-15:00
- Letter Sequence Labeling for Compound Splitting: Jianqiang Ma, Verena Henrich and Erhard Hinrichs
- Automatic Detection of Intra-Word Code-Switching: Dong Nguyen and Leonie Cornips
- Read my points: Effect of animation type when speech-reading from EMA data: Kristy James and Martijn Wieling
- Predicting the Direction of Derivation in English Conversion: Max Kisselew, Laura Rimell, Alexis Palmer and Sebastian Padó
- Morphological Segmentation Can Improve Syllabification: Garrett Nicolai, Lei Yao and Grzegorz Kondrak
- Towards a Formal Representation of Components of German Compounds: Thierry Declerck
Session 4: Phonology
- 15:00: Towards robust cross-linguistic comparisons of phonological networks: Philippa Shoemark, Sharon Goldwater, James Kirby and Rik Sarkar
Coffee break, 15:30-16:00
Session 5: Morphology
- 16:00: Morphotactics as Tier-Based Strictly Local Dependencies: Alena Aksenova, Thomas Graf and Sedigheh Moradi
- 16:30: A Multilinear Approach to the Unsupervised Learning of Morphology: Anthony Meyer and Markus Dickinson
- 17:00: Inferring Morphotactics from Interlinear Glossed Text: Combining Clustering and Precision Grammars: Olga Zamaraeva
Paper Submission
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 available at: https://www.softconf.com/acl2016/sigmorphon16/
Organizers
- Micha Elsner, The Ohio State University
- Sandra Kuebler, Indiana University
Email address to contact workshop organizers: sigmorphon2016@gmail.com
Program Committee
- Adam Albright, MIT
- Kelly Berkson, Indiana University
- Damir Cavar, Indiana University
- Grzegorz Chrupała, Tilburg University
- Çağrı Çöltekin, University of Tübingen
- Ewan Dunbar, Laboratoire de Sciences Cognitives et Psycholinguistique, Paris
- Jason Eisner, Johns Hopkins University
- Valerie Freeman, University of Washington
- Sharon Goldwater, University of Edinburgh
- Nizar Habash, NYU Abu Dhabi
- David Hall, Semantic Machines
- Mike Hammond, University of Arizona
- Jeffrey Heinz, University of Delaware
- Colin de la Higuera, University of Nantes
- Ken de Jong, Indiana University
- Gaja Jarosz, Amherst
- Greg Kobele, University of Chicago
- Greg Kondrak, University of Alberta
- Kimmo Koskenniemi, University of Helsinki
- Karen Livescu, TTI Chicago
- Kemal Oflazer, CMU Qatar
- Jeff Parker, Brigham Young
- Jelena Prokic, Philipps-Universitaet Marburg
- Andrea Sims, OSU
- Kairit Sirts, Macquarie University
- Richard Sproat, Google
- Reut Tsarfaty, Weizmann Institute
- Sami Virpioja, Aalto University
- Shuly Wintner, University of Haifa
Special thanks to reviewers who were recruited late in the process to deal with an unexpected number of submissions!
Shared Task: Morphological Reinflection
Main site: http://ryancotterell.github.io/sigmorphon2016/
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 hosting a shared task on morphological reinflection in 2016, held at ACL in Berlin, Germany.
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 2016 workshop. The task organizers will write an overview paper with descriptions and summaries of the different approaches taken and their results.
Questions about the shared task can be sent to sigmorphon-shared-task-2016-organizers@googlegroups.com. More information about the task, including training and development data sets for the target languages of varying morphological complexity is available at the shared task home page.
Shared Task: Important dates
- December 20, 2015 - Training data, evaluation scripts and baseline system released
- April 1, 2016 - Training data for surprise languages released
- April 20, 2016 - Test input data released; participants run systems
- April 25, 2016 - System outputs collected
- April 30, 2016 - System results to participants
- May 8, 2016 - Shared task system papers due
- June 5, 2016 - Notification of Acceptance
- June 22, 2016 - Camera-ready paper due
- August 11, 2016 - Workshop
Shared Task: Organizers
- Ryan Cotterell (Johns Hopkins University)
- Mans Hulden (University of Colorado)
- Christo Kirov (Johns Hopkins University)
- John Sylak-Glassman (Johns Hopkins University)