#emnlp2022 search results
الكمبيوتر حرفيا يكتب الشعر. الأبيات التي في الصورة لم يكتبها إنسان ولكن حاسوب أصم! شغل رائع لمريم عرابي #wanlp, #EMNLP2022
EMNLP is witnessing one of rarest moments you can experience in the Gulf area ... RAIN 🌧️🌧️⚡ #EMNLP2022
While I'm not at #EMNLP2022, we have two works on the intersection of RL + NLP. RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning (arxiv.org/abs/2205.12548) Efficient (Soft) Q-Learning for Text Generation with Limited Good Data (arxiv.org/abs/2106.07704)
🙌🙌🏽Putting African languages on the map: We’re thrilled to announce AfroLID, a neural lang ID tool for 517 African languages and varieties. W @IfeAdebara, @arelmadany & Alcoba to be presented 2day at @emnlpmeeting. Join us 9:00am AD, Hall A-B. @UBCLangScis @mbzuai #EMNLP2022 1/n
Very exciting keynote speech by @nazneenrajani at @emnlpmeeting about more than 75K models at @huggingface! I think they should change their emoji from 🤗 to 😱 #EMNLP2022
Welcome to EMNLP 2022 in Abu Dhabi! We are glad to announce a record attendance number of more than 3000 attendees. 1,629 are in-person and 1,316 are virtual as of last night with many more in-person and virtual registrations as of today! #EMNLP2022
Woohoo we won #EMNLP2022 best demo! 🤗 That’s three in a row for @huggingface 🤯🔥 2020 - Transformers 2021 - Datasets 2022 - Evaluate & Evaluation on the Hub
Big congratulations to @i_abufarha (and myself 😊) for winning the best paper award at @WANLP_Ar An excellent award to conclude his last piece of research of his PhD. #EMNLP2022 #WANLP2022 #ArabicNLP
We ⚠️Investigate the Benefits of Free-form Rationales in our #EMNLP2022 findings work, from both the human and the model perspectives. For humans, do rationales aid human interpretability? For models, do rationales boost the model performance? (0/n)
What machine translation errors are evaluation metrics sensitive to and to what extent? Check out DEMETR - dataset to diagnose MT evaluation metrics #EMNLP2022 (P4 Board 1) work with @Nishant95R @kthai1618 @yixiao_song @Anki98765 @MohitIyyer (1/5) 📜Paper arxiv.org/abs/2210.13746
How can we create a sentence summarization model using only LLM-generated summaries as training data, and end up with a much smaller, better quality, controlled summarizer than the ones generated by the model we started with? This is what we tackle in Referee, @ #EMNLP2022! 1/n
Slowly coming back to earth (+ timezone) after a fantastic time at #emnlp2022. It's truly a privilege to get to spend a week nerding out with colleagues and catching up with friends while exploring a new destination. Looking forward to many more!
We won #EMNLP2022 Honorable Mention Long Paper!!!🎉🎉 Thank you so much @emnlpmeeting for the recognition, I’m so excited and honored ☺️
How can we explain language model predictions? We use contrastive explanations to interpret LMs and show that they: - are better aligned with linguistic rules - improve model simulatability - help us characterize how LMs make decisions arxiv.org/abs/2202.10419 (w/@gneubig) 🧵1/7
Made it to Abu Dhabi! Hello #EMNLP2022 and here is the evening view passing the Grand Mosque from the airport 🕌
I appreciate the huge efforts made to organize a conference like #EMNLP2023 , but last year's poster sessions' setup was by FAR superior to this year's! It's a year late, but thanks @nyhabash for all your efforts organizing #EMNLP2022 in "Abu Dhabi", you raised our standard!
Leonie from @CisLmu is presenting now, stop by if you would like to find out about this intriguing question:
Details: • Paper: arxiv.org/pdf/2211.05673…, presented at #EMNLP2022. • Authors: @kr0niker, Alexey Tikhonov, @yorgos_pantis, Charlotte Schubert, Jürgen Jost.
📢 Attention #EMNLP23 reviewers! Your role in shaping the future of #NLP is crucial. Take a moment to refresh on best practices by checking out this informative link from #EMNLP2022 on the art of reviewing: 2022.emnlp.org/blog/Short-Pie…. Let's ensure quality and fairness!
This is a type of task for "domain expert humans". It's in the same spirit as our previous paper, "Logical Fallacy Detection" #EMNLP2022, where people do not necessarily manage, but are super important for our society (e.g., fighting against false belief) arxiv.org/abs/2202.13758
The second paper is on MasakhaNER 2.0 - an expansion of MasakhaNER dataset to 20 African languages in terms of size and language coverage #EMNLP2022
Glad to inform you that MasakhaNER 2.0 has been accepted to #EMNLP2022 , we expanded MasakhaNER to 20 African languages. Great work by @MasakhaneNLP @gneubig @seb_ruder @shrutirij @dklakow Michael Beukman, Chester Palen-Michel, @ConstantineLig @alabi_jesujoba @Shmuhammadd ...
Next, we have a non-archival presentation of a #EMNLP2022 paper by @LAWeissweiler: "The Better Your Syntax, the Better Your Semantics? Probing Pretrained Language Models for the English Comparative Correlative" #mwe2023
[2/4] My #EACL2023 paper can probably give you an overview of the state of the art of RST parsing in English: Though it doesn't include an #EMNLP2022 paper: aclanthology.org/2022.findings-…
📢 Check out our #EACL2023 paper 📢 Why Can't Discourse Parsing Generalize? A Thorough Investigation of the Impact of Data Diversity 📄 janetlauyeung.github.io/files/2023.eac… 👩💻 github.com/janetlauyeung/… 🕺 See you in Dubrovnik, Croatia 🇭🇷 [1/7]
github.com
GitHub - janetlauyeung/crossGENRE4RST: Supplementary Materials for EACL2023: Why Can’t Discourse...
Supplementary Materials for EACL2023: Why Can’t Discourse Parsing Generalize? A Thorough Investigation of the Impact of Data Diversity - janetlauyeung/crossGENRE4RST
主著論文（EMNLP2022 findings）のソースコード公開しました！ Very happy to announce that we have released our code associated with the paper published in #EMNLP2022! Sorry for the delay but hope that the code helps you. github.com/megagonlabs/Ty…
EMNLPで発表した論文が公開されました。 論文では、少ないラベルリソースでの効果的かつ高速なActive learning手法を提案しました。キーとなるアイデアは、1) ランダムサンプルで効率的な候補削減 2) 明示的なuncertaintyとdiversityの組合せによる精度向上です。 aclanthology.org/2022.findings-…
another reason why there are so many undergrads and high schoolers doing amazing AI/ML research rn it's virtually unheard of outside of our field for an undergrad to win best paper at a top conf (e.g. Anya Ji at #EMNLP2022)
AI moves fast, which means incumbents don't have a big advantage over new-joiners. For example, no one has >4 years of experience at prompting. Even 1k hours of practice makes you a world-class prompt engineer. This is not true for other fields (e.g., theoretical math/physics).
🎉 After a long and unexpected delay, #emnlp2022 Industry Track online proceedings is finally online! aclanthology.org/volumes/2022.e… Thanks all the authors for your patient! Specially thanks to my co-chair @aggielaz who has done the heavy lifting for making it happen!
Check out DANLI, a "Deliberative Agent for Following Natural Language Instructions" integrating neural and symbolic components for robust and interpretable task completion. New work from Prof. Joyce Chai's #SLEDLab. #EMNLP2022 youtu.be/WrHynGmCzZE
youtube.com
YouTube
DANLI: Deliberative Agent for Following Natural Language Instructions...
@aclmeeting Do we have no page limit / specific format in our response (to SAC) when committing the ARR reviews (@ReviewAcl) to #ACL2023 ? The 1st pic is a part of the commitment page, and the 2nd one is of #EMNLP2022, which required us to use ACL template and had 1-page limit
Check out DANLI: Deliberative Agent for Following Natural Language Instructions, new work from Prof. Joyce Chai's #SLEDLab. #EMNLP2022 youtube.com/watch?v=WrHynG…
youtube.com
YouTube
DANLI: Deliberative Agent for Following Natural Language Instructions...
Do you want to write better ethics consideration sections for your #NLProc papers? Here is the tutorial I promised during my poster at #emnlp2022 for my paper aclanthology.org/2022.emnlp-mai… Excited to learn more with @KarnFort1 @knmnyn @tsvetshop and you all!
👋 Missed our tutorial at #emnlp2022? You can now take it at your own pace! ⭐️ Slides: tinyurl.com/hh8k7mfy Thanks again to all my amazing co-presenters: Jeffrey Flanigan (@jmflanig), Ishan Jindal (@Ishanjindal28), Tim O’Gorman (@timjogorman), Nianwen Xue, and Martha Palmer
Our Pick of the week: Shaolei Zhang et al. #EMNLP2022 paper "Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translation". By @sarapapi aclanthology.org/2022.findings-… #nlproc #simultaneous #machinetranslation
In simultaneous translation, finding the best way to encode source and target information is crucial to guide the model during inference. With the wait-info policy, the authors adapted the popular wait-k to work with information rather than tokens: arxiv.org/pdf/2210.11220…
#EMNLP2022 @emnlpmeeting Proceedings are finally out! #NLProc take a look at our paper "Enhancing and Evaluating the Grammatical Framework Approach to Logic-to-Text Generation" I presented at the #gemworkshop22 🔥 Paper: aclanthology.org/2022.gem-1.13/ Code: gitlab.nl4xai.eu/eduardo.calo/L…
#NLProc, are you interested in knowing more about proper #evaluation of #NLG systems from #logic? 🔥My #firstPhDpaper explores the challenges of logic-to-text generation and sets a precedent for devising thorough evaluations for this task. 💎@emnlpmeeting 🧵1/6
Finally, it’s here: #EMNLP2022 aclanthology.org/events/emnlp-2…
What is NLP's most exciting development of 2022? I asked five leading AI researchers (Alex Fraser @nazneenrajani @nyhabash @preslav_nakov @sebgehr). This is what they said. More in the new video on #EMNLP2022: youtube.com/watch?v=plCvF_…
Great to talk to @JayAlammar and see him feature work from my team @SILintl in this video from #EMNLP2022! Teaser: I'll also be working on some other content with Jay soon! Love what he and @CohereAI are doing!
Last month, I attended the #EMNLP2022 conference -- one of the main NLP conferences. I took a camera and recorded my experience and some of my conversations with leading researchers. Watch it here! youtube.com/watch?v=plCvF_… A glimpse of what's exciting now and what's coming up!
Can LMs introspect the commonsense knowledge that underpins the reasoning of QA? In our #EMNLP2022 paper, we show that relatively small models (<< GPT-3), trained with RLMF (RL with Model Feedback), can generate natural language knowledge that bridges reasoning gaps. ⚛️ (1/n)
الكمبيوتر حرفيا يكتب الشعر. الأبيات التي في الصورة لم يكتبها إنسان ولكن حاسوب أصم! شغل رائع لمريم عرابي #wanlp, #EMNLP2022
Where does generative retrieval have a significant advantage over bi-encoder retrieval? Our #EMNLP2022 paper "Generative Multi-hop Retrieval" shows that the answer is 🦘multi-hop🦘 retrieval! (2.5x higher score when the # of hops is large, and the oracle # of hops is unknown) 1/9
Can instruction tuning improve zero and few-shot performance on dialogue tasks? We introduce InstructDial, a framework that consists of 48 dialogue tasks created from 59 openly available dialogue datasets #EMNLP2022🚀 Paper 👉 arxiv.org/abs/2205.12673 Work done at @LTIatCMU 🧵👇
Our paper on Systematic Error Analysis and Labeling (SEAL) 🦭 has been accepted at EMNLP demo track 🎉 Problem: How can we help users find systematic bugs in their models? Eg: Image classification model on low light images, sentiment classifier on gym reviews #emnlp2022
While I'm not at #EMNLP2022, we have two works on the intersection of RL + NLP. RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning (arxiv.org/abs/2205.12548) Efficient (Soft) Q-Learning for Text Generation with Limited Good Data (arxiv.org/abs/2106.07704)
🙌🙌🏽Putting African languages on the map: We’re thrilled to announce AfroLID, a neural lang ID tool for 517 African languages and varieties. W @IfeAdebara, @arelmadany & Alcoba to be presented 2day at @emnlpmeeting. Join us 9:00am AD, Hall A-B. @UBCLangScis @mbzuai #EMNLP2022 1/n
Coming to you live from Edinburgh, my #emnlp2022 Findings poster and I, during the virtual poster session of #BlackboxNLP at 4PM in Abu Dhabi (noon UTC). Find me at stand 492 in Gathertown to learn more about the Bottleneck Compositionality Metric @iatitov and I propose!
Happy to share our #EMNLP2022 paper on Factual Multimodal Summarization! A multimodal factuality metric (CLIPBERTScore), a meta-eval benchmark (MuFaME), & improving factuality of multimodal summarization via img selection + RL arxiv.org/abs/2211.02580 cc: @mohitban47 @uncnlp 🧵
Woohoo we won #EMNLP2022 best demo! 🤗 That’s three in a row for @huggingface 🤯🔥 2020 - Transformers 2021 - Datasets 2022 - Evaluate & Evaluation on the Hub
During the poster session of today's Multilingual Representation Learning (MRL) Workshop at #EMNLP2022, #AI researchers Saher Esmeir, @tudelft's @ArthurCamara & our @edgarmeij are presenting their paper "Entity Retrieval from Multilingual Knowledge Graphs" bloom.bg/3Bf6dAD
Super excited to share our work, "Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing" to appear @emnlpmeeting, w/ @TuhinChakr and @hhexiy Paper: arxiv.org/abs/2210.13669 Project Website: copoet-emnlp.github.io #emnlp2022 #NLProc
YONO: You Only Need One Model for Open-domain Question Answering uses one transformer-based reader to also do retrieval—with pre-computation—and reranking for SotA modest-parameter-count models. Haejun Lee @samsungresearch, @AshwinParanjape &c. #emnlp2022 arxiv.org/abs/2112.07381
Very exciting keynote speech by @nazneenrajani at @emnlpmeeting about more than 75K models at @huggingface! I think they should change their emoji from 🤗 to 😱 #EMNLP2022
👋 Missed our tutorial at #emnlp2022? You can now take it at your own pace! ⭐️ Slides: tinyurl.com/hh8k7mfy Thanks again to all my amazing co-presenters: Jeffrey Flanigan (@jmflanig), Ishan Jindal (@Ishanjindal28), Tim O’Gorman (@timjogorman), Nianwen Xue, and Martha Palmer
Something went wrong.
Something went wrong.
United States Trends
- 1. Kim Davis 4,428 posts
- 2. Pond 218K posts
- 3. #IDontWantToOverreactBUT N/A
- 4. $BNKK 1,096 posts
- 5. Semper Fi 7,503 posts
- 6. Go Birds 6,440 posts
- 7. Happy 250th 10.6K posts
- 8. #MondayMotivation 41.4K posts
- 9. #MYNZ N/A
- 10. $LMT $450.50 Lockheed F-35 N/A
- 11. $SENS $0.70 Senseonics CGM N/A
- 12. $APDN $0.20 Applied DNA N/A
- 13. Obergefell 3,055 posts
- 14. Obamacare 208K posts
- 15. Good Monday 48.8K posts
- 16. Edmund Fitzgerald 6,158 posts
- 17. Veterans Day 20.6K posts
- 18. Victory Monday 3,243 posts
- 19. #USMC 1,560 posts
- 20. Rudy Giuliani 31.8K posts