2022Q3 Reports: SIGTYP

From Admin Wiki
Jump to navigation Jump to search
The printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.

Summary

SIGTYP is ACL's special interest group on computational approaches to linguistic typology.

President: Ekaterina Vylomova

Secretary: Ryan Cotterell

At Large: Eitan Grossman, Edoardo M. Ponti, Silvia Luraghi, Alexis Palmer

Membership

The SIG was officially approved on Dec, 28 2019. As of July 2022, the total number of members has reached 436. We are planning to hold a membership drive to further promote growth within the SIG.

Workshop

In summer 2019 we organized the first workshop on typology for polyglot NLP (co-located with ACL 2019). In total, 48 attendees registered for the workshop (excluding organizers and keynote speakers). In autumn (November) 2020, we ran the second (virtual) workshop on computational research in linguistic typology (co-located with EMNLP 2020). In total, ~50 attendees registered for the workshop. In summer (July) 2021, we organized the third (virtual) workshop on computational typology and multilingual NLP (co-located with NAACL 2021). We developed our own virtual infrastructure (https://sigtyp.github.io/ws2021-schedule.html), ran several sessions during 24 hours to allow members from different time zones attend any session they prefer. According to our records, in total ~130 unique participants attended the sessions. In July 2022, we organized the fourth (hybrid) workshop on computational typology and multilingual NLP (co-located with NAACL 2022 that took place in Seattle). We developed our own virtual infrastructure (https://sigtyp.github.io/ws2022-sigtyp-schedule.html). According to the NAACL 2022 workshop chairs, ~70 ACL members registered for the workshop. According to our records, there were about 60-70 participants in the in-person part, and ~60 unique participants attended the virtual session.


Organizers of the SIGTYP 2022 workshop:

Ekaterina Vylomova, Hila Gonen, Jonas Pfeiffer, Edoardo M. Ponti, Alexey Sorokin, Andrey Shcherbakov, Sabrina J. Mielke, Gabriella Lapesa, Harald Hammarström, Pranav A, Ryan Cotterell, Ritesh Kumar

Keynote Speakers:

Kristen Howell, Isabel Papadimitriou, Graham Neubig

Proceedings: https://aclanthology.org/volumes/2022.sigtyp-1/

Later this year, we will have a second event organized under the SIGTYP umbrella, The Second Workshop on Multilingual Representation Learning (MRL): https://sigtyp.github.io/ws2022-mrl.html Organizers of the MRL 2022 workshop:

Duygu Ataman, Orhan Firat, Hila Gonen, Jamshidbek Mirzakhalov, Kelechi Ogueji, Sebastian Ruder, Gözde Gül Şahin

Shared Tasks

In 2022, SIGTYP offered a shared task on the prediction of cognate reflexes. In the task, we addressed one major task in historical linguistics: given cognates sets sets across languages, reconstruct missing entries (mainly relying on regular sound correspondences). Our data was taken from the Lexibank repository which offers wordlists from 100 standardized datasets (List et al. 2021. In the repository, a larger collection of datasets come with cognate sets provided by experts and with phonetic transcriptions which were standardized by the Lexibank team. Our development data, which users should use to test and design their models, consisted of 10 CLDF datasets of varying size, language families, and time depths.

Organizers of the SIGTYP 2022 Shared Task:

Johann-Mattis List, Ekaterina Vylomova, Robert Forkel, Nathan Hill, Ryan Cotterell

Overview: https://aclanthology.org/2022.sigtyp-1.7/

We are also currently running a shared task associated with the MRL workshop, The 1st Shared Task on Multilingual Clause-level Morphology: https://sigtyp.github.io/st2022-mrl.html

Organizers of the MRL 2022 Shared Task:

Omer Goldman, Reut Tsarfaty, Djame Seddah, Benjamin Muller, Benoît Sagot, Hila Gonen, Jamshidbek Mirzakhalov, Kelechi Ogueji,Francesco Tinner, Duygu Ataman

Other Activities (Online)

SIGTYP website and logo

We developed SIG’s website ([1]). It is constantly being updated with new information on workshops, shared tasks, members, and other information. We also designed a group’s logo: [2]

SIGTYP Lecture Series ([3])

IN 2021, every week we invite a speaker either from NLP or linguistic typology to present their research. We pre-record the talk in four ~15min parts and then play them having live discussions after each. For this purpose, we created our own Youtube and Bilibili (China) channels.

Youtube: https://www.youtube.com/channel/UCaSWMbnmduXYlbWGEWLedww/about

Bilibili: https://space.bilibili.com/1055445444

SIGTYP Lecture Hosts:

Olga Zamaraeva, Joe Brucker, Eleanor Chodroff, Pranav A, Ekaterina Vylomova, Ryan Cotterell

We are planning to continue this activity in the second half of 2022.

SIGTYP digest ([4])

Each month we invite members of the community to submit short abstracts or summaries of their recent papers to our monthly newsletter. This allows keeping track of the progress in the field and promoting everyone’s work.

Editors:

Ekaterina Vylomova, Pranav A, Eleanor Chodroff, Tiago Pimentel, Ryan Cotterell

Twitter account ([5])

We engage more members by keeping our Twitter account constantly updated with retweets of recent papers, talks, and other materials on linguistic typology, multilinguality, and low-resource NLP. As of July 2022, we have 1071 followers.

Managers:

Ekaterina Vylomova, Ryan Cotterell, Joe Brucker, Edoardo M Ponti

Mailing Lists

We created organizational structure for SIGTYP, e.g. Google groups for: 1) SIGTYP members; 2) SIGTYP Exec; 3) SIGTYP shared task organizers.


Elections

As secretary, Ryan Cotterell will be organizing the elections over the coming months. He is going to follow Garrett Nicolai's procedure at SIGMORPHON for remote voting.