Difference between revisions of "2022Q3 Reports: SIGMORPHON"
| Line 1: | Line 1: | ||
| − | This is the | + | This is the 2021-2022 annual report for SIGMORPHON, ACL's special interest group for computational morphology, phonology, and phonetics. |
== Membership == | == Membership == | ||
Revision as of 11:29, 3 August 2023
This is the 2021-2022 annual report for SIGMORPHON, ACL's special interest group for computational morphology, phonology, and phonetics.
Membership
The SIG membership is documented in the following table, observing 25% growth from 157 to 196 members in the past 5 years. We are planning to hold a membership drive to further promote growth of the SIG.
| Year | Membership |
|---|---|
| 2022 | 196 |
| 2021 | 175 |
| 2020 | 176 |
| 2019 | 176 |
| 2018 | 157 |
| 2017 | 167 |
| 2016 | 157 |
| 2015 | 150 |
| 2014 | 144 |
| 2013 | 142 |
| 2012 | 137 |
| 2011 | 120 |
| 2010 | 105 |
| 2009 | 96 |
| 2008 | 90 |
| 2007 | 73 |
| 2006 | 55 |
Workshop
The 19th SIG workshop was held at NAACL 2022, organized by Garrett Nicolai and Eleanor Chodroffl. The workshop has successfully converted from a biennial workshop to an annual one. This is especially important now as our community is undergoing rapid growth.
The 2022 Workshop had 18 submissions from which the program committee selected 10 for publication (56% acceptance rate). There were two invited talks: Laura Gwilliams, and Gasper Begus. The workshop was held in a hybrid format, with both live attendees at NAACL, and virtual attendees via Zoom.
In 2022, SIGMORPHON held an open solicitation for shared tasks, selecting 3. Each task was separately proposed by an organizing committee, and separately approved by the SIG Executive Committee, who worked with the organizing committee in some cases. This structure was inspired by other groups (SIGSEM and SIGNLL) that run multiple shared tasks, and we expect to keep it in future years.
Task 0
SIGMORPHON's seventh installment of its inflection generation shared task is divided into two parts: Re-inflection, and acquisition trajectories.
In the first part, participants designed a model that learned to generate morphological inflections from a lemma and a set of morphosyntactic features of the target form.
In the second part, instead of predicting well-formedness of nonce word forms, systems were instead evaluated on their ability to generalize over naturalistic low-resource inputs. The organizers prepared data to determine systems' learning trajectories and compare them against the wealth of data that has been collected about human learning trajectories for three famous problems: English past tense, German noun plurals, and Arabic noun plurals.
Task 1
The SIGMORPHON shared task on grapheme-to-phoneme conversion expanded on the task from last year, with new languages and data.
Task 2
Task 2 was new to this year’s workshop, and involved the segmentation of words into morphemes in both contextual and context-free scenarios.
Membership drive
A bug in the Google group was discovered, which was automatically rejecting new members; once this bug was fixed, we saw membership increase by more than 10%. We are now expecting to conduct a membership drive in the coming year.
Elections
The elected officers of the SIG are listed at [1], and are serving a 2-year term. The next elections are scheduled to take place in January, 2023.