#naturallanguagegeneration — Public Fediverse posts

Reminder that I administer the "some NLG people" Discord server for researchers and others interested in #NaturalLanguageGeneration / #TextGeneration. DM me if you want an invite link :)

It's been a while since I wrote an #introduction for folks who are #NewHere.

I'm a #queer #Catholic computational #linguist who works on #NaturalLanguageGeneration and lives in #Scotland. An #immigrant multiple times over, I was born in #SouthAfrica, grew up in the USA (in #Florida), did my PhD in #Germany, and moved here in 2019. I enjoy #VideoGames, #VideoEssays, #OpenMic nights, and #running. I happen to be #nonbinary and love #languages.

#INLG2024 submission deadline is in 4 weeks! How are your papers coming together?

If you work on #NaturalLanguageGeneration, #TextGeneration (with or w/o #LLMs)

All deadlines are Anywhere on Earth (UTC-12)
• START system regular paper submission deadline: May 31, 2024
• ARR commitment to INLG deadline via START system: June 24, 2024
• START system demo paper submission deadline: June 24, 2024
• Notification: July 15, 2024

More info: https://inlg2024.github.io/calls.html

The first #CallForPapers for #INLG2024 is now out!

If you work on #NaturalLanguageGeneration, #TextGeneration (with or w/o #LLMs)

All deadlines are Anywhere on Earth (UTC-12)
• START system regular paper submission deadline: May 31, 2024
• ARR commitment to INLG deadline via START system: June 24, 2024
• START system demo paper submission deadline: June 24, 2024
• Notification: July 15, 2024
• Camera ready: August 16, 2024
• Conference: 23-27 September 2024

More info: https://inlg2024.github.io/calls.html

You might have heard me claim that most #NLG is #LowResource (not just #NaturalLanguageGeneration for #LowResourceLanguages). If you want to hear me explain a bit more, my talk from last year's #GEM workshop at #EMNLP2022 is now up online: https://underline.io/lecture/66771-most-nlg-is-low-resource-here-s-what-we-can-do-about-it

Wondering how you join #SIGGEN, the Special Interest Group for Natural Language Generation (part of the ACL)?

Sign up for the mailing list: https://www.jiscmail.ac.uk/cgi-bin/wa-jisc.exe?SUBED1=SIGGEN&A=1

It's that simple! You'll stay up to date with conferences and workshops and submission deadlines, as well as job postings and journal special issues.

#NaturalLanguageGeneration #TextGeneration #NLProc #NLP #PleaseBoost

A wee #introduction since there are lots of folks joining or rejoining the fediverse in general and Mastodon in particular.

I'm Dave, a #queer #Catholic who runs and sings for fun. I play #VideoGames (currently #Titanfall2) and watch a lot of #Dropout (#Dimension20, #PlayItByEar, #GameChanger are faves), #VideoEssays, and #anime.

I recently went to my first #burn (not #BurningMan, tho) and am digging the inclusive accepting culture.

At work I'm a #researcher in #ComputationalLinguistics focused on #NaturalLanguageGeneration and #psycholinguistics methods. You could say my dayjob is trying to develop a more ethical #ChatGPT

Feel free to ask me questions about #Mastodon if you are #NewHere

Similarly, you may want a so-called #MeaningRepresentation, some structured representation of the information conveyed by a text or a linguistically motivated semantic representation of the text. These annotations are essential for my work in #NaturalLanguageGeneration / #NLG, and a big struggle for the community is coming up with ways to build #corpora for different tasks, domains, genres, or languages which also have the kinds of MRs our systems use.

In my own work, I'm working to adapt simpler models which are not as data-hungry to perform data-to-text #NLG in #LowResource settings. Part of this effort will involve exploring #MultitaskLearning and #Pipeline approaches to neural #NaturalLanguageGeneration.

Follow me if you want more content related to these topics, though be advised that this is a whole-person account and I will talk about things other than work as well.

This is not to say, however, that I think these models are useless. I think the interesting question is how to integrate these models into systems that express a particular meaning, a la data-to-text #NaturalLanguageGeneration. Whether this involves #PromptEngineering, integrating them into the decoder for #seq2seq models, or some other more clever application remains to be seen. I am looking forward to seeing how #LLM/s get used for #NLG going forward.

Around 2015 and 2016 we saw sequence-to-sequence (#seq2seq) models applied to data-to-text #NLG for the first time. These models were trained end-to-end and were very exciting because it raised the prospect of reducing the amount of hand-crafted #GrammarEngineering one would have to do to create a #NaturalLanguageGeneration system.