#eacl2023 search results
While Russia continues to wage a war against all of Ukrainian people, EACL had workshop organizers affiliated with Russian companies-sponsors of the war. Here's our official statement: shorturl.at/gqVWZ #eacl2023
🚨Join us on May 3rd to see our #eacl2023 poster and presentation on "NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages". This is our initiative to create an NLP resource for underrepresented 🇮🇩Indonesian languages. arxiv.org/abs/2205.15960
Retrieval-augmented Language has shown great performance on knowledge-intensive tasks. In our recent #EACL2023 paper QA-Memory (arxiv.org/abs/2204.04581), we explore the possibility to augment pre-trained language models (T5) with QA-pairs as memory. QA pairs as the knowledge ..
Walking the Walls of Dubrovnik after the end of the main conference of #EACL2023! Excited for workshops tomorrow!!
Thanks to @egrefen for his great #eacl2023 keynote! Some take-aways: - LLMs struggle to grasp pragmatics - data quality and diversity are key to LLM performance - open-ended RL can help with automatic data selection #NLProc
CODI deadline today! Got discourse work in #EACL2023 #ACL2023 Findings? Submit to us and present! sites.google.com/view/codi-2023…
Thrilled to receive 'Outstanding Paper Award' at @eaclmeeting 2023 for our paper 'Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions', with @Mihir3009, @megamor2 and @cbaral #EACL2023 #NLProc #research #NLP #Award #LLMs #bias #data #quality
Our last fantastic invited speaker at #eacl2023 was Joyce Chai, who told us about how to enable language communication between humans and agents #NLProc
Our second inspiring #eacl2023 keynote by Kevin Munger “Chatbots for Good (and Evil)” offering lots of food for thoughts about how humans are becoming more bot-like #NLProc
Our short paper "Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples" with @Bollegala and @chokkanorg got accepted to the #EACL2023🎉 We propose a method to compare intrinsic gender bias measures without relying on human-annotations!
The CODI workshop calls for #ACL2023NLP #EACL2023 Findings presentations! If your work is relevant to discourse, and if you would like to present at CODI in Toronto this July, please submit to us! sites.google.com/view/codi-2023…
First #eacl2023 poster session in progress. Make sure to check the info screens if you’re looking for a specific poster. #NLProc
Such a shame that both of my posters at #EACL2023 were at the same time, and I couldn't talk to everyone who came up to my stands! But I hope ye enjoyed the designs at least 🫏👑 I was asked multiple times how I made them, so here is a thread on poster design @AcademicChatter
That’s a wrap for #eacl2023! Thanks to @vlachos_nlp and conference cat (secret programme chair #3) for the excellent collaboration. Was nice to see so many attendees enjoying the conference this week, and have some time to do the same. #NLProc
It was super nice to find out that some people remembered the donkey poster from #EACL2023 and recognised me by the style ☺️
Such a shame that both of my posters at #EACL2023 were at the same time, and I couldn't talk to everyone who came up to my stands! But I hope ye enjoyed the designs at least 🫏👑 I was asked multiple times how I made them, so here is a thread on poster design @AcademicChatter
#EACL2023: Finding the Law: legal IR +GNNs aclanthology.org/2023.eacl-main… #ACL2023: VendorLink: Identifying & Linking Vendors on Darknet Markets aclanthology.org/2023.acl-long.… #FAccT2023: Examining the risks and opportunities of a right to repair for mobile apps ora.ox.ac.uk/objects/uuid:a…
We found that many approaches to long-range transformers (such as sparsified pattern, recurrence, and kernels) don’t actually translate into NLP task performance (arxiv.org/abs/2202.07856, #EACL2023). Can we fix it?
The networking experience is something else in person. Otherwise, it’s a complete waste of resources and somehow many in #nlproc seem to be OK with it. I still feel guilty that I paid over 1000$ to only register for #EACL2023! And that doesn’t include traveling to the venue.
At #EACL2023, I presented a probing approach that uses the distillability of a sentence embedding transformer to a syntactic neural module net as a proxy for the transformer's compositionality. aclanthology.org/2023.eacl-main… youtube.com/watch?v=_t1beP…
youtube.com
YouTube
Syntax-guided Neural Module Distillation to Probe Compositionality in...
"Shironaam" corpus is now available at @huggingface! This is the largest news headline generation dataset of a low-resource language (Bengali). #NLProc #eacl2023 Link: huggingface.co/datasets/diale… 🧵[1/3]
As we are approaching the end of May, I'd like to say how great this month was! I participated at #EACL2023 in Croatia and also, got a long paper accepted at #ACL2023NLP. I also gave three talks at three countries, met old friends and made new ones too. Here is a thread 🙂
At @eaclmeeting, Amazon researchers showed how to use generative AI to address the problem of extreme multilabel classification (XMC), or classifying inputs when the space of possible labels is enormous. #GenAI #EACL2023 amazon.science/blog/using-gen…
The CODI workshop calls for #ACL2023NLP #EACL2023 Findings presentations! If your work is relevant to discourse, and if you would like to present at CODI in Toronto this July, please submit to us! sites.google.com/view/codi-2023…
Can’t agree more! Was a volunteer at NAACL 2022 and EACL 2023 🤠 Bonus: sometimes the friendships can go way beyond just a single conference! @davidelct @DamoGreta 🤗 we exchanged snacks and tea we got from 🇳🇱🇩🇪🇮🇹 at #EACL2023 (unfortunately they are in my delayed/missing 🧳)
GPT-4 puede hablar con fluidez. Pero, ¿cuánto 🦜 es? Probamos 1 versión simplificada de nuestra tarea de PSD presentada en #eacl2023, predecir la similitud de frases en diferentes contextos. frase-en-context.github.io 🧵 lo bueno y lo malo de GPT-4 en esta interesante prueba de PSD
GPT-4 can speak fluently. But how much of a 🦜is it? We test GPT-4 on a simplified ver. of our PSD task presented at #eacl2023, i.e. predicting phrase similarity given different contexts. phrase-in-context.github.io 🧵on the good & bad of GPT-4 on this interesting PSD test ... 1/8
And that's a wrap for our special session on Clinical NLP! Enjoy the coffee break now, followed by the poster session. We reconvene for the final oral session at 17:15! #mwe2023 #eacl2023
GPT-4 can speak fluently. But how much of a 🦜is it? We test GPT-4 on a simplified ver. of our PSD task presented at #eacl2023, i.e. predicting phrase similarity given different contexts. phrase-in-context.github.io 🧵on the good & bad of GPT-4 on this interesting PSD test ... 1/8
⭐️Introducing PiC - a Phrase-in-Context dataset for Phrase Understanding and Semantic Search.⭐️ BERT-like contextualized word embeddings have been a de facto standard in #NLProc. Yet, learning contextualized *phrase* embeddings remains a grand challenge. 🧵 1/10
🥲 Who said there can’t be a second time? Now I’m even more convinced that my 🧳 wanted to hang out in Germany (this time Frankfurt) as opposed to being stuck with me I laughed so hard when I didn’t see my luggage on the 🛄 AGAIN 🫠 🥹 Highlights of my #EACL2023
BTW for the first time in my life 🙃 my checked bag got lost 🥲 I guess my luggage wanted to hang out in Munich a little bit more 🫠
🎉 Congrats to the LongEval paper on winning #EACL2023 Outstanding Paper Award! LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization: semanticscholar.org/paper/LongEval…
Happy to share our #BestPaperAward from the @MultiWord Workshop at #EACL2023 💬 Detecting Idiomatic Multiword Expressions 🏥 in Clinical Terminology 📖 using Definition-Based Representation Learning @FremyCompany @Alfiya_Kh @ThoMeestr 🧵
Our #EACL2023 paper presents FewShotTextGCN for few-shot learning on graphs. We learn from scratch (without using #LLMs) and outperform #LLMs on a range of languages using as little as 20 training samples. Joint work with @Mrvoh_nlp @KatiaShutova #NLProc aclanthology.org/2023.eacl-main…
EACL2023のproceedingsが公開されてますね（遅い）。 主著の"JBLiMP: Japanese Benchmark of Linguistic Minimal Pairs"が採択されています！ (Findings)ご興味のある方はぜひ〜 aclanthology.org/2023.findings-… #eacl2023
I am glad to share our work titled "Annotating PubMed Abstracts with MeSH Headings using Graph Neural Network". The paper was recently presented at the Insights workshop @ EACL 2023. I am incredibly thankful to all the people involved in the project. #NLProc #EACL2023 #GNN
Congrats Nhung's paper "Span-based Named Entity Recognition by Generating and Compressing Information | Nhung Nguyen, Makoto Miwa and Sophia Ananiadou" #EACL2023 #UniMan_NLP Manchester NLP group.
Two co-authored papers from @NlpTohoku were accepted by #eacl2023 (1 main, 1 findings)! Both are about the symbolic reasoning ability of neural learners. @AACL_SRW 2022 had also encouraged our non-archival Findings work with the best paper award. Thanks! x.gd/aaclsrw2022
🚨Join us on May 3rd to see our #eacl2023 poster and presentation on "NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages". This is our initiative to create an NLP resource for underrepresented 🇮🇩Indonesian languages. arxiv.org/abs/2205.15960
Finally had the pleasure of 👀ing one of the famous conference 🐱s on the last day of #EACL2023 🐈⬛ It was such a wonderful experience, and the mission to catch up with old friends and make new friends has been successfully accomplished 🕺🏻 See y’all in Toronto #ACL2023 🤗
Walking the Walls of Dubrovnik after the end of the main conference of #EACL2023! Excited for workshops tomorrow!!
Retrieval-augmented Language has shown great performance on knowledge-intensive tasks. In our recent #EACL2023 paper QA-Memory (arxiv.org/abs/2204.04581), we explore the possibility to augment pre-trained language models (T5) with QA-pairs as memory. QA pairs as the knowledge ..
📢Hey #EACL2023 @eaclmeeting folks: come and ask me about the inaugural joint 🚨@LrecColing2024 🚨happening next year in ✨Turin (Torino), Italy – 20-25 May, 2024✨! 1st CFP out soon! Please RT! lrec-coling-2024.lrec-conf.org
CODI deadline today! Got discourse work in #EACL2023 #ACL2023 Findings? Submit to us and present! sites.google.com/view/codi-2023…
Our short paper "Comparing Intrinsic Gender Bias Evaluation Measures without using Human Annotated Examples" with @Bollegala and @chokkanorg got accepted to the #EACL2023🎉 We propose a method to compare intrinsic gender bias measures without relying on human-annotations!
Sticking around Dubrovnik for the EACL workshops? Come check out our Findings paper on generating synthetic conversation datasets! I'll be presenting a poster tomorrow (May 5) at the Insights from Negative Results in NLP workshop at 4:30pm, in Elafiti 4. #EACL2023 #NLProc
Oh, the✨PLACES✨you'll go [with synthetic data]! Augmentation helps with low-resource data, but how do you augment tasks which doesn't exist? In our EACL Findings paper, we show LMs can synthesize high-quality dyadic and multiparty conversation corpora. arxiv.org/abs/2302.03269
![maximillianc_'s tweet image. Oh, the✨PLACES✨you'll go [with synthetic data]!
Augmentation helps with low-resource data, but how do you augment tasks which doesn't exist?
In our EACL Findings paper, we show LMs can synthesize high-quality dyadic and multiparty conversation corpora.
arxiv.org/abs/2302.03269](https://pbs.twimg.com/media/FpMVHuDXsAEz2uL.png)
Thrilled to receive 'Outstanding Paper Award' at @eaclmeeting 2023 for our paper 'Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions', with @Mihir3009, @megamor2 and @cbaral #EACL2023 #NLProc #research #NLP #Award #LLMs #bias #data #quality
TOMORROW May 4 - don't miss Prof. Joyce Chai's talk during Session 12 Keynote at #EACL2023 #NLProc! ⬇️ 2023.eacl.org/program/main/
Thanks to @egrefen for his great #eacl2023 keynote! Some take-aways: - LLMs struggle to grasp pragmatics - data quality and diversity are key to LLM performance - open-ended RL can help with automatic data selection #NLProc
Excited for EACL 2023 @eaclmeeting. Here is a summary of our posters. See you at the poster session if you are attending! #eacl2023 #NLProc #NLP #LLM
Something went wrong.
Something went wrong.
United States Trends
- 1. TOP CALL 3,843 posts
- 2. Good Monday 26.6K posts
- 3. AI Alert 1,384 posts
- 4. #BaddiesUSA 65.5K posts
- 5. #centralwOrldXmasXFreenBecky 528K posts
- 6. SAROCHA REBECCA DISNEY AT CTW 548K posts
- 7. NAMJOON 53.8K posts
- 8. #LingOrmDiorAmbassador 283K posts
- 9. #MondayMotivation 7,277 posts
- 10. Check Analyze N/A
- 11. Token Signal 1,836 posts
- 12. Market Focus 2,550 posts
- 13. Rams 30.4K posts
- 14. #LAShortnSweet 24.5K posts
- 15. Vin Diesel 1,560 posts
- 16. DOGE 182K posts
- 17. Scotty 10.5K posts
- 18. Chip Kelly 9,222 posts
- 19. Stacey 24.4K posts
- 20. Ahna 7,931 posts