2021Q3 Reports: SIGTYP - Revision history

Ivri at 03:32, 11 July 2021

2021-07-11T03:32:54Z

← Older revision		Revision as of 03:32, 11 July 2021
Line 53:		Line 53:

	SIGTYP Lecture Hosts:		SIGTYP Lecture Hosts:
	Olga Zamaraeva, Joe Brucker, Eleanor Chodroff, Ekaterina Vylomova, Ryan Cotterell		Olga Zamaraeva, Joe Brucker, Eleanor Chodroff, Pranav A, Ekaterina Vylomova, Ryan Cotterell

	'''SIGTYP digest ([https://sigtyp.github.io/blog.html])'''		'''SIGTYP digest ([https://sigtyp.github.io/blog.html])'''

Ivri at 03:31, 11 July 2021

2021-07-11T03:31:13Z

← Older revision		Revision as of 03:31, 11 July 2021
Line 51:		Line 51:

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

			SIGTYP Lecture Hosts:
			Olga Zamaraeva, Joe Brucker, Eleanor Chodroff, Ekaterina Vylomova, Ryan Cotterell

	'''SIGTYP digest ([https://sigtyp.github.io/blog.html])'''		'''SIGTYP digest ([https://sigtyp.github.io/blog.html])'''

	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.		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 ([https://twitter.com/sig_typ])'''		'''Twitter account ([https://twitter.com/sig_typ])'''

	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 2021, we have 879 followers.		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 2021, we have 879 followers.

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

	'''Mailing Lists'''		'''Mailing Lists'''

Ivri at 03:25, 11 July 2021

2021-07-11T03:25:00Z

← Older revision		Revision as of 03:25, 11 July 2021
Line 20:		Line 20:


	Organizers of 2021 workshop:		Organizers of the SIGTYP 2021 workshop:
	Ekaterina Vylomova, Elizabeth Salesky, Sabrina Mielke, Gabriella Lapesa, Ritesh Kumar, Harald Hammarström, Ivan Vulić, Anna Korhonen, Roi Reichart, Edoardo Maria Ponti, Ryan Cotterell		Ekaterina Vylomova, Elizabeth Salesky, Sabrina Mielke, Gabriella Lapesa, Ritesh Kumar, Harald Hammarström, Ivan Vulić, Anna Korhonen, Roi Reichart, Edoardo Maria Ponti, Ryan Cotterell

Ivri at 03:12, 11 July 2021

2021-07-11T03:12:08Z

← Older revision		Revision as of 03:12, 11 July 2021
Line 11:		Line 11:
	== Membership ==		== Membership ==

	The SIG was officially approved on Dec, 28 2019. In July 2021, the total number of members has reached 380. We are planning to hold a membership drive to further promote growth within the SIG.		The SIG was officially approved on Dec, 28 2019. As of July 2021, the total number of members has reached 380. We are planning to hold a membership drive to further promote growth within the SIG.

	== Workshop ==		== Workshop ==
Line 58:		Line 58:
	'''Twitter account ([https://twitter.com/sig_typ])'''		'''Twitter account ([https://twitter.com/sig_typ])'''

	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. In July 2021, we ~~had~~ 879 followers.		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 2021, we have 879 followers.

	'''Mailing Lists'''		'''Mailing Lists'''

Ivri at 02:49, 11 July 2021

2021-07-11T02:49:13Z

← Older revision		Revision as of 02:49, 11 July 2021
Line 16:		Line 16:

	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 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 ~~approaches to~~ linguistic typology (co-located with EMNLP 2020). In total, ~50 attendees registered for the workshop.		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 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.

Ivri at 02:48, 11 July 2021

2021-07-11T02:48:26Z

← Older revision		Revision as of 02:48, 11 July 2021
Line 1:		Line 1:
	== Summary ==		== Summary ==

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

	President: Ekaterina Vylomova		President: Ekaterina Vylomova
Line 17:		Line 17:
	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 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 approaches to linguistic typology (co-located with EMNLP 2020). In total, ~50 attendees registered for the workshop.		In autumn (November) 2020, we ran the second (virtual) workshop on computational approaches to 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 ~~approaches to linguistic~~ typology (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 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.


Line 44:		Line 44:

	'''SIGTYP Lecture Series ([https://sigtyp.github.io/lectures.html])'''		'''SIGTYP Lecture Series ([https://sigtyp.github.io/lectures.html])'''

	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.		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.		For this purpose, we created our own Youtube and Bilibili (China) channels.

Ivri at 02:44, 11 July 2021

2021-07-11T02:44:39Z

Ivri at 02:43, 11 July 2021

2021-07-11T02:43:15Z

← Older revision		Revision as of 02:43, 11 July 2021
Line 25:		Line 25:
	Keynote Speakers:		Keynote Speakers:
	Claire Bowern, Miryam de Lhoneux, Johannes Bjerva, David Yarowsky		Claire Bowern, Miryam de Lhoneux, Johannes Bjerva, David Yarowsky

			Proceedings: [https://aclanthology.org/volumes/2021.sigtyp-1/]

	== Shared Tasks ==		== Shared Tasks ==

	In 2021, SIGTYP offered a shared task on the robust prediction of language ID from speech. In the task, we addressed one major issue: for many low-resource and endangered languages, only single-speaker recordings may be available. Therefore, such conditions require domain and speaker-invariant language ID systems. We asked the participants to build systems that will be trained on largely single-speaker speech from one domain, but evaluated on data in other domains recorded from speakers under different recording circumstances, mimicking more realistic low-resource scenarios. In total, 3 teams participated in the task. The results demonstrate that the task is challenging.		In 2021, SIGTYP offered a shared task on the robust prediction of language ID from speech. In the task, we addressed one major issue: for many low-resource and endangered languages, only single-speaker recordings may be available. Therefore, such conditions require domain and speaker-invariant language ID systems. We asked the participants to build systems that will be trained on largely single-speaker speech from one domain, but evaluated on data in other domains recorded from speakers under different recording circumstances, mimicking more realistic low-resource scenarios. In total, 3 teams participated in the task. The results demonstrate that the task is challenging.

			Organizers of the 2021 Shared Task:
			Elizabeth Salesky, Badr M Abdullah, Sabrina J Mielke, Elena Klyachko, Oleg Serikov, Edoardo Ponti, Ritesh Kumar, Ryan Cotterell, Ekaterina Vylomova

			Overview: https://aclanthology.org/2021.sigtyp-1.11/

	== Other Activities (Online) ==		== Other Activities (Online) ==

Ivri at 02:28, 11 July 2021

2021-07-11T02:28:52Z

← Older revision		Revision as of 02:28, 11 July 2021
Line 28:		Line 28:
	== Shared Tasks ==		== Shared Tasks ==

	In 2021, SIGTYP offered a shared task on the robust prediction of language ID from speech. In the task, we addressed one major issue: for many low-resource and endangered languages, only single-speaker recordings may be available. Therefore, such conditions require domain and speaker-invariant language ID systems. We asked the participants to build systems that will be trained on largely single-speaker speech from one domain, but evaluated on data in other domains recorded from speakers under different recording circumstances, mimicking more realistic low-resource scenarios. In total, 3 teams participated in the task. Th results demonstrate that the task is challenging.		In 2021, SIGTYP offered a shared task on the robust prediction of language ID from speech. In the task, we addressed one major issue: for many low-resource and endangered languages, only single-speaker recordings may be available. Therefore, such conditions require domain and speaker-invariant language ID systems. We asked the participants to build systems that will be trained on largely single-speaker speech from one domain, but evaluated on data in other domains recorded from speakers under different recording circumstances, mimicking more realistic low-resource scenarios. In total, 3 teams participated in the task. The results demonstrate that the task is challenging.

	== Other Activities (Online) ==		== Other Activities (Online) ==

Ivri: Created page with "== Summary == SIGTYP is ACL's special interest group on linguistic typology. President: Ekaterina Vylomova Secretary: Ryan Cotterell At Large: Eitan Grossman, Edoardo M...."

2021-07-11T02:24:04Z

Created page with "== Summary == SIGTYP is ACL's special interest group on linguistic typology. President: Ekaterina Vylomova Secretary: Ryan Cotterell At Large: Eitan Grossman, Edoardo M...."

New page

== Summary ==

SIGTYP is ACL's special interest group on 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. In July 2021, the total number of members has reached 380. 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 approaches to 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 approaches to linguistic typology (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.

Organizers of 2021 workshop:
Ekaterina Vylomova, Elizabeth Salesky, Sabrina Mielke, Gabriella Lapesa, Ritesh Kumar, Harald Hammarström, Ivan Vulić, Anna Korhonen, Roi Reichart, Edoardo Maria Ponti, Ryan Cotterell

Keynote Speakers:
Claire Bowern, Miryam de Lhoneux, Johannes Bjerva, David Yarowsky

== Shared Tasks ==

In 2021, SIGTYP offered a shared task on the robust prediction of language ID from speech. In the task, we addressed one major issue: for many low-resource and endangered languages, only single-speaker recordings may be available. Therefore, such conditions require domain and speaker-invariant language ID systems. We asked the participants to build systems that will be trained on largely single-speaker speech from one domain, but evaluated on data in other domains recorded from speakers under different recording circumstances, mimicking more realistic low-resource scenarios. In total, 3 teams participated in the task. Th results demonstrate that the task is challenging.

== Other Activities (Online) ==

'''SIGTYP website and logo'''

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

'''SIGTYP Lecture Series ([https://sigtyp.github.io/lectures.html])'''
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 digest ([https://sigtyp.github.io/blog.html])'''

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.

'''Twitter account ([https://twitter.com/sig_typ])'''

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.

'''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.

← Older revision		Revision as of 02:44, 11 July 2021
Line 26:		Line 26:
	Claire Bowern, Miryam de Lhoneux, Johannes Bjerva, David Yarowsky		Claire Bowern, Miryam de Lhoneux, Johannes Bjerva, David Yarowsky

	Proceedings: [https://aclanthology.org/volumes/2021.sigtyp-1/]		Proceedings: https://aclanthology.org/volumes/2021.sigtyp-1/

	== Shared Tasks ==		== Shared Tasks ==
Line 45:		Line 45:
	'''SIGTYP Lecture Series ([https://sigtyp.github.io/lectures.html])'''		'''SIGTYP Lecture Series ([https://sigtyp.github.io/lectures.html])'''
	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.		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:		For this purpose, we created our own Youtube and Bilibili (China) channels.

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

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

Line 55:		Line 57:
	'''Twitter account ([https://twitter.com/sig_typ])'''		'''Twitter account ([https://twitter.com/sig_typ])'''

	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.		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. In July 2021, we had 879 followers.

	'''Mailing Lists'''		'''Mailing Lists'''