mastodon.world is one of the many independent Mastodon servers you can use to participate in the fediverse.
Generic Mastodon server for anyone to use.

Server stats:

8.1K
active users

#nlproc

0 posts0 participants0 posts today
Roman Klinger<p>If you share <a class="hashtag" rel="nofollow noopener" href="https://bsky.app/search?q=%23NLProc" target="_blank">#NLProc</a> research interests with me, my conference report for <a class="mention" href="https://bsky.app/profile/aclmeeting.bsky.social" rel="nofollow noopener" target="_blank">@aclmeeting.bsky.social</a> <a class="hashtag" rel="nofollow noopener" href="https://bsky.app/search?q=%23ACL2025" target="_blank">#ACL2025</a> might be interesting for you – I highlight the papers that I personally found particularly relevant for our own research. <a href="https://www.romanklinger.de/blog/2025-08-01-acl/" rel="nofollow noopener" target="_blank">www.romanklinger.de/blog/2025-08...</a></p>
Benjamin Han<p>Apple @ <a href="https://sigmoid.social/tags/ACL2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ACL2025</span></a>: Schedule &amp; Accepted Papers.</p><p><a href="https://machinelearning.apple.com/updates/apple-at-acl-2025" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">machinelearning.apple.com/upda</span><span class="invisible">tes/apple-at-acl-2025</span></a></p><p><a href="https://sigmoid.social/tags/research" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>research</span></a> <a href="https://sigmoid.social/tags/conference" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>conference</span></a> <a href="https://sigmoid.social/tags/nlp" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>nlp</span></a> <a href="https://sigmoid.social/tags/nlproc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>nlproc</span></a></p>
UKP Lab<p>Work by: Max Glockner (UKP Lab), Xiang Jiang (Amazon AGI), Leonardo F. R. Ribeiro (Amazon AGI), Iryna Gurevych (UKP Lab), and Markus Dreyer (Amazon AGI).</p><p> 📄 Paper: <a href="https://arxiv.org/abs/2505.05949" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">arxiv.org/abs/2505.05949</span><span class="invisible"></span></a><br> 💾 Data: <a href="https://huggingface.co/datasets/mglockner/neoqa" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">huggingface.co/datasets/mglock</span><span class="invisible">ner/neoqa</span></a><br> 💻 Code: <a href="https://github.com/amazon-science/neoqa" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">github.com/amazon-science/neoqa</span><span class="invisible"></span></a></p><p><a href="https://sigmoid.social/tags/ACL2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ACL2025</span></a> <a href="https://sigmoid.social/tags/NLProc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NLProc</span></a> <a href="https://sigmoid.social/tags/EvidenceBasedAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>EvidenceBasedAI</span></a> <a href="https://sigmoid.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a></p><p>(3/3)</p><p>The original post was published on Twitter/X by Markus Dreyer:<br><a href="https://x.com/markusdr/status/1924873660969652306" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">x.com/markusdr/status/19248736</span><span class="invisible">60969652306</span></a></p>
UKP Lab<p>Also consider following the authors Aniket Pramanick (Ubiquitous Knowledge Processing (UKP) Lab)‬, Yufang Hou (IT:U- Interdisciplinary Transformation University Austria, IBM Research), Saif M Mohammad (National Research Council Canada / Conseil national de recherches Canada), and Iryna Gurevych (Ubiquitous Knowledge Processing (UKP) Lab).</p><p>🗺️ See you at <a href="https://sigmoid.social/tags/ACL2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ACL2025</span></a> in Vienna</p><p>(2/2)</p><p><a href="https://sigmoid.social/tags/NLProc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NLProc</span></a> <a href="https://sigmoid.social/tags/ACL2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ACL2025</span></a> <a href="https://sigmoid.social/tags/AI4Science" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI4Science</span></a> <a href="https://sigmoid.social/tags/ACL2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ACL2025</span></a></p>
Federico Pianzola<p>Great work by <a class="mention" href="https://bsky.brid.gy/ap/did:plc:b6utqwwbqzvdhhvke4mbbfjw" rel="nofollow noopener" target="_blank">@robertonavigli.bsky.social</a> and the Sapienza NLP team on coreference resolution for (very long) books! tl;dr: it's hard! <a class="hashtag" rel="nofollow noopener" href="https://bsky.app/search?q=%23DigitalHumanities" target="_blank">#DigitalHumanities</a> <a class="hashtag" rel="nofollow noopener" href="https://bsky.app/search?q=%23ComputationalLiteraryStudies" target="_blank">#ComputationalLiteraryStudies</a> <a class="hashtag" rel="nofollow noopener" href="https://bsky.app/search?q=%23NLProc" target="_blank">#NLProc</a> <a href="https://arxiv.org/abs/2507.12075" rel="nofollow noopener" target="_blank">arxiv.org/abs/2507.12075</a><br><br><a href="https://arxiv.org/abs/2507.12075" rel="nofollow noopener" target="_blank">BOOKCOREF: Coreference Resolut...</a></p>
UKP Lab<p>Multilingual sentence encoders face conflicting demands — not only across languages, but also between monolingual and cross-lingual tasks. Optimizing for one language or task type can degrade performance in others. 🧩 𝗟𝗲𝘁’𝘀 𝗺𝗮𝗸𝗲 𝘁𝗵𝗲𝗺 𝗺𝗼𝗱𝘂𝗹𝗮𝗿. Our new method uses separate specialization and alignment adapters to avoid interference. </p><p>🔗Project: <a href="https://ukplab.github.io/acl2025-modular-sentence-encoders/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">ukplab.github.io/acl2025-modul</span><span class="invisible">ar-sentence-encoders/</span></a></p><p><a href="https://sigmoid.social/tags/NLProc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NLProc</span></a></p><p>(1/🧵)</p>
Tristan Miller<p>I'm featured in a video from the University of Manitoba promoting studies at the Department of Computer Science. (I'm still accepting graduate student applications!) <a href="https://mastodon.social/tags/NLProc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NLProc</span></a> <a href="https://mastodon.social/tags/ComputationalLinguistics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ComputationalLinguistics</span></a></p><p><a href="https://youtu.be/5vgh0IutGHk?si=zTM0b3NJ8QTlelGJ" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">youtu.be/5vgh0IutGHk?si=zTM0b3</span><span class="invisible">NJ8QTlelGJ</span></a></p>
UKP Lab<p>And consider following the authors Chen Cecilia Liu, Anna Korhonen, and Iryna Gurevych if you are interested in more information or an exchange of ideas.</p><p>See you in Vienna! <a href="https://sigmoid.social/tags/ACL2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ACL2025</span></a></p><p><a href="https://sigmoid.social/tags/ResponsibleAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ResponsibleAI</span></a> <a href="https://sigmoid.social/tags/CulturalNLP" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CulturalNLP</span></a> <a href="https://sigmoid.social/tags/NLProc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NLProc</span></a> <a href="https://sigmoid.social/tags/ACL2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ACL2025</span></a></p>
The Data Therapist<p>7. Neural Machine Translation for Low-Resource Languages with Monolingual Data and Back-Translation<br>8. Multilingual Sarcasm Detection </p><p>Ideal turnaround: 4 weeks. <br>If you can review pls reply/DM with first+last name, email for reviews, and paper number(s) from the list above.</p><p>Please boost! Thanks!</p><p><a href="https://mastodon.social/tags/NLP" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NLP</span></a> <br><a href="https://mastodon.social/tags/NLProc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NLProc</span></a> <br><a href="https://mastodon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a></p>
UKP Lab<p>[...] enhance their robustness and relevance in real world applications.</p><p>A significant contribution to the field of context aware NLP and a milestone for Tilman personally and academically.</p><p>We wish him all the best for his next steps!</p><p>(3/3)</p><p><a href="https://sigmoid.social/tags/NLProc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NLProc</span></a> <a href="https://sigmoid.social/tags/PhDDefense" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PhDDefense</span></a> <a href="https://sigmoid.social/tags/ContextualAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ContextualAI</span></a> <a href="https://sigmoid.social/tags/UKPLab" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>UKPLab</span></a> <a href="https://sigmoid.social/tags/TUDarmstadt" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TUDarmstadt</span></a></p>
The Data Therapist<p>I’m looking for reviewers for these journal articles:<br>1. Phonology/IPA and LLM (not for English)<br>2. LLM math/logic abilities in diff cultural contexts<br>3. Prosody-syntax interact in low resource lang</p><p>Ideal turnaround: 4 weeks. If you can review pls reply/DM with first+last name &amp; email for reviews.</p><p>Thanks!<br><a href="https://mastodon.social/tags/NLP" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NLP</span></a> <a href="https://mastodon.social/tags/NLProc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NLProc</span></a></p>
Emiel van Miltenburg<p>Does anyone know whether there are automatic solutions to detect either "ghost references" (academic sources that do not actually exist) or improper citations (misrepresenting claims in earlier work)?</p><p>Would be a very interesting <a href="https://scholar.social/tags/nlp" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>nlp</span></a> <a href="https://scholar.social/tags/nlproc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>nlproc</span></a> challenge, and useful to flag potential fraud.</p>
Judith van Stegeren<p>New blogpost: <br>Lessons from the first year of my PhD</p><p>I finished my PhD in computer science more than three years ago. Now that I have a little bit of mental distance from my PhD time, I'm going through my research diary to see if there's stuff in there that can be useful for other people.</p><p>Apparently I'm incapable of writing short-form texts, so here is part 1. ;)</p><p><a href="https://www.judithvanstegeren.com/blog/lessons-learned-in-phd-year-one/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">judithvanstegeren.com/blog/les</span><span class="invisible">sons-learned-in-phd-year-one/</span></a></p><p><a href="https://fosstodon.org/tags/academia" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>academia</span></a> <a href="https://fosstodon.org/tags/nlproc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>nlproc</span></a> <a href="https://fosstodon.org/tags/phd" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>phd</span></a> <a href="https://fosstodon.org/tags/phdlife" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>phdlife</span></a> <a href="https://fosstodon.org/tags/research" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>research</span></a></p>
DW Innovation<p>(2/2)</p><p>Nicolas Patz is at the Europeana Conference in Warsaw, leading a panel on "Telling stories with tech: XR, 3D and AI for <a href="https://mastodon.social/tags/CulturalHeritage" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CulturalHeritage</span></a>". <br>This one will also feature EU-funded projects <span class="h-card" translate="no"><a href="https://mastodon.social/@transmixr" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>transmixr</span></a></span>, <span class="h-card" translate="no"><a href="https://mastodon.social/@presence" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>presence</span></a></span>, @Eureka3D-XR and 5D Culture. </p><p>Warsaw: <a href="https://pro.europeana.eu/page/conference" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">pro.europeana.eu/page/conferen</span><span class="invisible">ce</span></a></p><p>If you happen to be in Dublin or Warsaw, don't hesitate to say hi &amp; have a cup of coffee with the ReCos. ☕ </p><p><a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/NLProc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NLProc</span></a> <a href="https://mastodon.social/tags/XR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>XR</span></a> <a href="https://mastodon.social/tags/3D" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>3D</span></a></p>
Michael Piotrowski<p>I was just sent this photo, supposedly taken in 1994: Björn Beutel, developer of the Malaga language, and myself are working in the CLUE (Computational Linguistics University of Erlangen) lab.</p><p>I’m a bit hesitant to tag this <a href="https://mastodon.acm.org/tags/retrocomputing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>retrocomputing</span></a> ;-)</p><p><a href="https://mastodon.acm.org/tags/CompLing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CompLing</span></a> <a href="https://mastodon.acm.org/tags/NLProc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NLProc</span></a> <a href="https://mastodon.acm.org/tags/Erlangen" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Erlangen</span></a></p>
Tatjana Scheffler<p>🚨 <a href="https://fediscience.org/tags/ESSLLI2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ESSLLI2025</span></a> - Last chance for early bird registration (May 31)!<br>👉 Logic<br>👉 Language <br>👉 Information<br>Really interesting courses and the Ruhr area is much more interesting than it is known for! ✨ <br><a href="https://fediscience.org/tags/nlproc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>nlproc</span></a> <a href="https://fediscience.org/tags/logic" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>logic</span></a> <a href="https://fediscience.org/tags/linguistics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>linguistics</span></a> <a href="https://fediscience.org/tags/summerschool" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>summerschool</span></a> <br><a href="https://2025.esslli.eu/registration.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">2025.esslli.eu/registration.ht</span><span class="invisible">ml</span></a></p>
UKP Lab<p>Are LM more than their behavior? 🤔 </p><p>Join our Conference on Language Modeling (COLM) workshop and explore the interplay between what LMs answer and what happens internally ✨</p><p>See you in Montréal 🍁</p><p>CfP: shorturl.at/sBomu<br>Page: shorturl.at/FT3fX<br>Reviewer Nomination: shorturl.at/Jg1BP </p><p><a href="https://sigmoid.social/tags/nlproc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>nlproc</span></a> <a href="https://sigmoid.social/tags/interpretability" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>interpretability</span></a></p>
Roman Klinger<p>I'll give a talk this Thursday at 5:45 at Universität zu Köln: "Adapting Language Models for the Analysis of Real World Textual Data – Train the model, change the prompt, or adapt the data?" – the talk is based on <a href="https://aclanthology.org/2025.coling-main.375/" rel="nofollow noopener" target="_blank">aclanthology.org/2025.coling-...</a> and <a href="https://arxiv.org/abs/2412.11653" rel="nofollow noopener" target="_blank">arxiv.org/abs/2412.11653</a> <a class="hashtag" href="https://bsky.app/search?q=%23NLProc" rel="nofollow noopener" target="_blank">#NLProc</a></p>
UKP Lab<p>Is In-Context Learning (ICL) in LLMs Memorisation? Emergence? Some Algorithmic Capability? 🤔</p><p>📢New work exploring ICL in LLMs: arxiv.org/abs/2505.11004 </p><p>💡Key Finding: <br>ICL capabilities are linked to token frequency 🤨</p><p>Strap in for the unexpected 🤯</p><p>A 🧵👇 <a href="https://sigmoid.social/tags/NLProc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NLProc</span></a></p>
Tatjana Scheffler<p>✨European Summer School for Logic, Language and Information 2025✨ in Bochum, Germany: <br>- 47 courses &amp; workshops<br>- 4 exciting evening lectures<br>- social events <br>- explore the Ruhr area<br>Early bird registration deadline: May 31!<br><a href="https://fediscience.org/tags/esslli2025" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>esslli2025</span></a> <a href="https://fediscience.org/tags/esslli" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>esslli</span></a> <a href="https://fediscience.org/tags/logic" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>logic</span></a> <a href="https://fediscience.org/tags/linguistics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>linguistics</span></a> <a href="https://fediscience.org/tags/compSci" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>compSci</span></a> <a href="https://fediscience.org/tags/nlproc" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>nlproc</span></a> <a href="https://fediscience.org/tags/summerSchool" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>summerSchool</span></a> <a href="https://fediscience.org/tags/rub" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>rub</span></a> <a href="https://2025.esslli.eu/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">2025.esslli.eu/</span><span class="invisible"></span></a></p><p>Edit: Boosts appreciated 🤗</p>