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

Great to talk with @JayAlammar at #EMNLP2022, and I'm honored that he featured my team's research in his latest video! Check it out: https://youtu.be/plCvF_7qrmY

Quite enjoyed Mona Diab's (https://twitter.com/MonaDiab77/) #EMNLP2022 keynote today.

Lots of interesting work on #ResponsibleAI and #ResponsibleNLP. (Even if a lot of it is coming from Meta/Facebook 😬)

One of the earlier mentions was TCT (https://github.com/facebookresearch/text_characterization_toolkit) which re-implements a lot of #CohMetrix text statistics to help researchers characterise the corpora they're training their models on

What a great way to kick new 2023 episodes of @practicalai! This week we are sharing a conversation I had at #EMNLP2022 with Just Zwennicker, Andiswa Bukula, Rooweither Mabuya & Bonaventure Dossou

Amazing researchers building SOTA #AI #NLProc for their communities. Listen here: https://changelog.com/practicalai/205

🦾 New episode of Practical AI! 🦾

While at #EMNLP2022, @dwhitena got a chance to sit down with an amazing group of researchers creating #NLP technology that actually works for their local language communities.

The group emphasized the need for more linguistically diverse NLP systems that work in scenarios of data scarcity, non-Latin scripts, rich morphology, etc. You don’t want to miss this one!

🎧 https://practicalai.fm/205

Paper Title:
Curriculum Prompt Learning with Self-Training for Abstractive Dialogue Summarization

Authors:
Changqun Li, Linlin Wang, Xin Lin, Gerard de Melo, Liang He

This is joint work with researchers from East China Normal University in Shanghai, including my former PhD student Linlin Wang, who is now a faculty member there, and, most importantly, her student collaborator Changqun Li.

Check out the #EMNLP2022 Paper for further details:
http://gerard.demelo.org/papers/dialogue-summarization.pdf
http://gerard.demelo.org/papers/dialogue-summarization.bib

2/2

Overwhelming amounts of dialogue are being recorded in social media, instant messaging apps, Slack channels, customer service interactions, and so on.

Wouldn't it be great if automated tools could provide us short, succinct summaries?

Here's talk I just gave at #EMNLP2022 about a new #LLM prompt learning method that works fairly well even when the training data is extremely limited.

https://speakerdeck.com/gdm/curriculum-prompt-learning-with-self-training-for-abstractive-dialogue-summarization

1/2

#NLP #NLProc #AI

Had a great time meeting people at #BlackboxNLP and #EMNLP2022 last week. You can see my talk as well as great talks by Lena Voita and Catherine Olsson on youtube here:

https://youtube.com/@blackboxnlp

We had lots of papers at #emnlp2022 … and lots of us were there in Abu Dhabi in person to present them!

https://ai.stanford.edu/blog/emnlp-2022/

@thelonious @trochee here, let me toot you the antidote: the #BenderRule winner of #emnlp2022 : Søgaard — chapeau!

https://preview.aclanthology.org/emnlp-22-ingestion/2022.emnlp-main.351.pdf

#nlp #nlproc

For all NLP folks out there: all #emnlp2022 papers now also discoverable in Zeta Alpha.

https://search.zeta-alpha.com/?q=&doc_sources=EMNLP&d=ly

Haven’t read it yet but the title and abstract give me a strong #BenderRule itch

https://preview.aclanthology.org/emnlp-22-ingestion/2022.emnlp-main.118.pdf

#NLP #NLProc #emnlp2022

I had a great conversation with José Souza and Ricardo Rei from Unbabel at #emnlp2022 about SOTA machine translation and quality estimation. Listen to it here on @practicalai: https://changelog.com/practicalai/204

#ai #NLProc

EMNLP2022 trip report: neuro-symbolic approaches in NLP are on the rise
https://keet.wordpress.com/2022/12/14/emnlp22-trip-report-neuro-symbolic-approaches-in-nlp-are-on-the-rise/
the report is longer than intended, yet still incomplete wrt the papers that aren’t (only) large language models, but also inject structured content, reasoners, or grammars to improve on a range of NLP tasks. #EMNLP2022

🤖 New episode of Practical AI! 🤖

José and Ricardo joined @dwhitena at #EMNLP2022 to discuss state-of-the-art machine translation, the WMT shared tasks, and quality estimation.

Among other things, they talk about Unbabel’s innovations in quality estimation including COMET, a neural framework for training multilingual machine translation (MT) evaluation models.

🎧 https://practicalai.fm/204 #ai #machinelearning #nlp

live from #emnlp2022 talking about #ChatGPT 🤖💬 I am 😊 to have had a short interview on #AlJazeeranews explaining why it's not new, what are the opportunities, the limitations and what does it mean for the future #nlproc #AI

🔗 to 🎥:
https://mediaview.aljazeera.com/video/0clqobCKIs

Well, I'm back from #emnlp2022 and catching up on email and end of year tasks. Great to learn so much and meet with great friends in Abu Dhabi!

Made it back home from #EMNLP2022! Thanks to the
organizers for this experience and thanks to all the wonderful people I was able to meet in person! 🥳

Summary of my current position on #ChatGPT:

(A post- #EMNLP2022 #nlproc 🧵 )

* it’s fun to play with (evident by 1M users in a few days)

* I started more skeptical about its usefulness beyond fun and PR, but I now think it can be useful for technical writing and other non-creative report writing (medical etc), *if post-edited / verified for correctness*

* this means you need to know what you are doing! In other words, it can be a good expert-aid tool (but not sure abt lay-person)

It was a wonderful time at #EMNLP2022, catching up and having research discussions with old friends and new.

Now that the week is done I hope we keep the conversations going! In addition to Twitter, would suggest Mastodon. Sign up https://sigmoid.social and cross-post (T ➡️ M).