Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
eupolicy.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
This Mastodon server is a friendly and respectful discussion space for people working in areas related to EU policy. When you request to create an account, please tell us something about you.

Administered by:

Server stats:

217
active users

eupolicy.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.8

#nlp

1 post1 participant0 posts today
Lenin alevski 🕵️💻<p>New Open-Source Tool Spotlight 🚨🚨🚨</p><p>Transform any URL into an LLM-ready input with `Reader`. Just prefix the URL with `<a href="https://r.jina.ai/`" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">r.jina.ai/`</span><span class="invisible"></span></a> for clean, readable content extraction. Perfect for enhancing agents &amp; RAG pipelines. <a href="https://infosec.exchange/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> <a href="https://infosec.exchange/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a></p><p>Need web search results for your LLM? Prepend queries with `<a href="https://s.jina.ai/`" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">s.jina.ai/`</span><span class="invisible"></span></a> to fetch top results—content included. E.g., `<a href="https://s.jina.ai/your+query`" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">s.jina.ai/your+query`</span><span class="invisible"></span></a> brings knowledge directly to your model. <a href="https://infosec.exchange/tags/AItools" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AItools</span></a> <a href="https://infosec.exchange/tags/DataEngineering" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DataEngineering</span></a> </p><p>Reader API now supports images! Captions are auto-generated for images missing alt tags, giving LLMs better context for reasoning and summarizing multimedia pages. <a href="https://infosec.exchange/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MachineLearning</span></a> <a href="https://infosec.exchange/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a></p><p>🔗 Project link on <a href="https://infosec.exchange/tags/GitHub" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>GitHub</span></a> 👉 <a href="https://github.com/jina-ai/reader" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">github.com/jina-ai/reader</span><span class="invisible"></span></a></p><p><a href="https://infosec.exchange/tags/Infosec" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Infosec</span></a> <a href="https://infosec.exchange/tags/Cybersecurity" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Cybersecurity</span></a> <a href="https://infosec.exchange/tags/Software" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Software</span></a> <a href="https://infosec.exchange/tags/Technology" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Technology</span></a> <a href="https://infosec.exchange/tags/News" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>News</span></a> <a href="https://infosec.exchange/tags/CTF" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>CTF</span></a> <a href="https://infosec.exchange/tags/Cybersecuritycareer" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Cybersecuritycareer</span></a> <a href="https://infosec.exchange/tags/hacking" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>hacking</span></a> <a href="https://infosec.exchange/tags/redteam" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>redteam</span></a> <a href="https://infosec.exchange/tags/blueteam" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>blueteam</span></a> <a href="https://infosec.exchange/tags/purpleteam" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>purpleteam</span></a> <a href="https://infosec.exchange/tags/tips" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>tips</span></a> <a href="https://infosec.exchange/tags/opensource" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>opensource</span></a> <a href="https://infosec.exchange/tags/cloudsecurity" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>cloudsecurity</span></a></p><p>— ✨<br>🔐 P.S. Found this helpful? Tap Follow for more cybersecurity tips and insights! I share weekly content for professionals and people who want to get into cyber. Happy hacking 💻🏴‍☠️</p>
Dirk Derom<p>VUB 🇧🇪 is hunting for a <a href="https://mastodon.social/tags/postdoc" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>postdoc</span></a> / <a href="https://mastodon.social/tags/Research" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Research</span></a> Engineer who vibes with <a href="https://mastodon.social/tags/nlp" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>nlp</span></a> + ontologies.</p><p>We juggle:<br>💻 Python &amp; transformers<br>🗂️ <a href="https://mastodon.social/tags/ontology" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ontology</span></a> craft<br>🔍 <a href="https://mastodon.social/tags/knowledgegraph" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>knowledgegraph</span></a> wizardry</p><p>Partial remote? Totally cool.</p><p>DM me if you’re curious — and feel free to boost! 🚀 <a href="https://mastodon.social/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a> <a href="https://mastodon.social/tags/semanticweb" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>semanticweb</span></a></p>
WriterOfMinds (she)<p>Small demo this month! I always wanted to be able to see Acuitas "thinking" and I've updated the semantic memory visualization to make that possible. <a href="https://writerofminds.blogspot.com/2025/06/acuitas-diary-85-june-2025.html" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">writerofminds.blogspot.com/202</span><span class="invisible">5/06/acuitas-diary-85-june-2025.html</span></a></p><p><a href="https://sigmoid.social/tags/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ArtificialIntelligence</span></a> <a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://sigmoid.social/tags/chatbots" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>chatbots</span></a> <a href="https://sigmoid.social/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a></p>
Mark Wyner Won’t Comply :vm:<p>What I told Siri to say (“I hate this sap smear across our windshield”) vs what Siri said.</p><p><a href="https://mas.to/tags/VoiceRecognition" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VoiceRecognition</span></a> <a href="https://mas.to/tags/Siri" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Siri</span></a> <a href="https://mas.to/tags/Apple" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Apple</span></a> <a href="https://mas.to/tags/VoiceUX" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>VoiceUX</span></a> <a href="https://mas.to/tags/NaturalLanguageDetection" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NaturalLanguageDetection</span></a> <a href="https://mas.to/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a></p>
Aaron<p>The only actual machine learning the system uses, aside from its purely emergent ability to learn language from context, is in the parser, where I adjust the probability of matching certain patterns based on prior success in understanding the user.</p><p><a href="https://techhub.social/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a><br><a href="https://techhub.social/tags/NLU" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLU</span></a></p>
Aaron<p>I wrote this code in my spare time, over about a decade. I wrote the parser, the knowledge graph, the conversational engine, everything from scratch in pure python. It starts out literally knowing nothing except English grammar, and learns everything from interactions with the user. These tests I posted... It is literally learning the words from context as I use them. It had no idea what a dog or an apple or the color red is until I tell it things about them.</p><p><a href="https://techhub.social/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a><br><a href="https://techhub.social/tags/NLU" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLU</span></a></p>
Aaron<p>Do you see how the system answers questions it doesn't know? That's right. It says, "I don't know." Say no to hallucinations.</p><p><a href="https://techhub.social/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a><br><a href="https://techhub.social/tags/NLU" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLU</span></a></p>
Aaron<p>Here's another passing unit test. Again, this is stuff I wrote almost a decade ago, before LLMs were even invented.</p><p> &gt; The brown dog bites me.<br> &gt; The black dog barks at me.<br> &gt; The dog that bites me hates me.<br> &gt; Which dog hates me?<br> &lt; The brown dog.<br> &gt; Does the brown dog bite me?<br> &lt; Yes.<br> &gt; Does the brown dog hate me?<br> &lt; Yes.<br> &gt; Does the black dog hate me?<br> &lt; I don't know.<br> &gt; Does the dog that barks at me hate me?<br> &lt; I don't know.<br> &gt; Is the brown dog the dog that bites me?<br> &lt; Yes.</p><p><a href="https://techhub.social/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a><br><a href="https://techhub.social/tags/NLU" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLU</span></a></p>
Aaron<p>Just dug out some of my code from almost a decade ago, pre-LLM, and got it working again. Some examples of what it could do, taken from actual passing unit tests, are below. Lines starting with &gt; are what the user says, and lines starting with &lt; are what the system says.</p><p> &gt; The apple is red.<br> &gt; The worm is in the apple.<br> &gt; The apple is in the basket.<br> &gt; Where is the worm?<br> &lt; In the apple.<br> &gt; Where is the apple?<br> &lt; In the basket.<br> &gt; Is the worm in the apple?<br> &lt; Yes.<br> &gt; Is the apple in the basket?<br> &lt; Yes.<br> &gt; Is the worm in the basket?<br> &lt; I don't know.<br> &gt; What is in the apple?<br> &lt; The worm.<br> &gt; Is the apple red?<br> &lt; Yes.</p><p><a href="https://techhub.social/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a><br><a href="https://techhub.social/tags/NLU" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLU</span></a></p>
Cheuk Ting Ho<p><a href="https://fosstodon.org/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a> expert Ines is back to speak at <a href="https://fosstodon.org/tags/PyData" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>PyData</span></a> London. Make sure you join the <a href="https://fosstodon.org/tags/FeministAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>FeministAI</span></a> party after her talk.</p><p><span class="h-card" translate="no"><a href="https://sigmoid.social/@ines" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>ines</span></a></span></p>
Seán Fobbe<p>Question for the digital humanities people:</p><p>Is there any good <a href="https://fediscience.org/tags/OpenSource" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenSource</span></a> graphical tool for natural language processing that is both easy to use and performs a reasonable number of analyses? </p><p>I am looking for something that the average lawyer or student with a couple of weeks training could operate.</p><p>Thanks!</p><p><a href="https://fediscience.org/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a> <a href="https://fediscience.org/tags/DigitalHumanities" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DigitalHumanities</span></a></p>
Leshem Choshen<p>Gradient norms rise at the end of training, and a new theory connects that to the learning loss when using weight decay.<br>AdamC and SGDC(orrected) multiply the weight decay by the learning rate and fix it. <br><a href="https://alphaxiv.org/pdf/2506.02285" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">alphaxiv.org/pdf/2506.02285</span><span class="invisible"></span></a><br>📈🤖🧠<br><a href="https://sigmoid.social/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ai</span></a> <a href="https://sigmoid.social/tags/ml" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ml</span></a> <a href="https://sigmoid.social/tags/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llm</span></a> <a href="https://sigmoid.social/tags/pretraining" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>pretraining</span></a> <a href="https://sigmoid.social/tags/nlp" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>nlp</span></a></p>
DiSC_uibk<p>Have you ever struggled to find the best document retrieval model for your project? Or had to combine multiple frameworks just to get a basic <a href="https://social.uibk.ac.at/tags/InformationRetrieval" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>InformationRetrieval</span></a> pipeline running?</p><p>Check out Rankify, developed by Abdelrahman Abdallah from the <a href="https://social.uibk.ac.at/tags/DataScience" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DataScience</span></a> Group <span class="h-card" translate="no"><a href="https://social.uibk.ac.at/@uniinnsbruck" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>uniinnsbruck</span></a></span>, which provides an all-in-one retrieval, re-ranking, and retrieval-augmented generation toolkit: <a href="https://www.doi.org/10.48763/000013" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="">doi.org/10.48763/000013</span><span class="invisible"></span></a></p><p><a href="https://social.uibk.ac.at/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://social.uibk.ac.at/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>MachineLearning</span></a> <a href="https://social.uibk.ac.at/tags/RAG" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RAG</span></a> <a href="https://social.uibk.ac.at/tags/OpenSource" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenSource</span></a> <a href="https://social.uibk.ac.at/tags/FOSS" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>FOSS</span></a> <a href="https://social.uibk.ac.at/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a> <a href="https://social.uibk.ac.at/tags/research" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>research</span></a></p>
Harald Klinke<p>💬 Want to use GPT-4, Claude, Gemini, Ollama &amp; more directly from R?<br>Meet {ellmer}: a powerful wrapper to access a wide range of LLM providers via a unified interface.<br>Includes function/tool calling, structured output, image input &amp; streaming!</p><p>📦 install.packages("ellmer")<br>📘 Docs: <a href="https://ellmer.tidyverse.org/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">ellmer.tidyverse.org/</span><span class="invisible"></span></a><br><a href="https://det.social/tags/rstats" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>rstats</span></a> <a href="https://det.social/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> <a href="https://det.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://det.social/tags/OpenSource" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenSource</span></a> <a href="https://det.social/tags/DataScience" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>DataScience</span></a> <a href="https://det.social/tags/RPackage" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RPackage</span></a> <a href="https://det.social/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a></p>
ESWC Conferences<p>📘 The 2nd NSLP 2025 Workshop is now underway at <a href="https://sigmoid.social/tags/ESWC2025" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ESWC2025</span></a>!<br>📍 Room 3 – Aurora III, Floor 0</p><p>NSLP brings together researchers focused on the processing, analysis, transformation, and utilization of scientific language and Research Knowledge Graphs (RKGs).</p><p>From papers to structured knowledge — this is where AI meets scientific publishing. 🧠📄🔗</p><p><a href="https://sigmoid.social/tags/NSLP2025" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NSLP2025</span></a> <a href="https://sigmoid.social/tags/ResearchKnowledgeGraphs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ResearchKnowledgeGraphs</span></a> <a href="https://sigmoid.social/tags/ScientificLanguage" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ScientificLanguage</span></a> <a href="https://sigmoid.social/tags/SemanticWeb" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SemanticWeb</span></a> <a href="https://sigmoid.social/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a> <a href="https://sigmoid.social/tags/KnowledgeGraphs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>KnowledgeGraphs</span></a> <a href="https://sigmoid.social/tags/ESWC2025" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ESWC2025</span></a> <a href="https://sigmoid.social/tags/AI4Science" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI4Science</span></a> <a href="https://sigmoid.social/tags/LinkedData" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LinkedData</span></a> <a href="https://sigmoid.social/tags/OpenScience" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenScience</span></a></p>
ESWC Conferences<p>🔗 More info: aiisc.ai/text2kg2025/ </p><p><a href="https://sigmoid.social/tags/TEXT2KG2025" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>TEXT2KG2025</span></a> <a href="https://sigmoid.social/tags/LLM" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>LLM</span></a> <a href="https://sigmoid.social/tags/KnowledgeGraphs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>KnowledgeGraphs</span></a> <a href="https://sigmoid.social/tags/SemanticWeb" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>SemanticWeb</span></a> <a href="https://sigmoid.social/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a> <a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a></p>
WriterOfMinds (she)<p>I started working on trial-and-error learning abilities for Acuitas this month! Notes on the technique I'm trying to establish here: <a href="https://writerofminds.blogspot.com/2025/05/acuitas-diary-84-may-2025.html" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">writerofminds.blogspot.com/202</span><span class="invisible">5/05/acuitas-diary-84-may-2025.html</span></a><br><a href="https://sigmoid.social/tags/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ArtificialIntelligence</span></a> <a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://sigmoid.social/tags/chatbots" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>chatbots</span></a> <a href="https://sigmoid.social/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a></p>
Harald Sack<p>Last week, we continued our <a href="https://sigmoid.social/tags/ISE2025" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ISE2025</span></a> lecture on distributional semantics with the introduction of neural language models (NLMs) and compared them to traditional statistical n-gram models. <br>Benefits of NLMs:<br>- Capturing Long-Range Dependencies<br>- Computational and Statistical Tractability<br>- Improved Generalisation<br>- Higher Accuracy</p><p><span class="h-card" translate="no"><a href="https://wisskomm.social/@fiz_karlsruhe" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>fiz_karlsruhe</span></a></span> <span class="h-card" translate="no"><a href="https://sigmoid.social/@fizise" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>fizise</span></a></span> <span class="h-card" translate="no"><a href="https://fedihum.org/@tabea" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>tabea</span></a></span> <span class="h-card" translate="no"><a href="https://fedihum.org/@sourisnumerique" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>sourisnumerique</span></a></span> <span class="h-card" translate="no"><a href="https://sigmoid.social/@enorouzi" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>enorouzi</span></a></span> <a href="https://sigmoid.social/tags/llms" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llms</span></a> <a href="https://sigmoid.social/tags/nlp" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>nlp</span></a> <a href="https://sigmoid.social/tags/AI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>AI</span></a> <a href="https://sigmoid.social/tags/lecture" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>lecture</span></a></p>
Seán Fobbe<p>🔔 NEU 🔔 </p><p>Alle 4566 Plenarprotokolle des Deutschen Bundestages von 1949 bis 2025 (Stichtag: 24. Mai) ab sofort im 'Corpus der Plenarprotokolle des Deutschen Bundestages' (CPP-BT) verfügbar.</p><p>Auch Einzelreden mit Name, ID und Fraktion der Redner:in!</p><p>🔶 Download 🔶 </p><p>💾 Datensatz - <a href="https://doi.org/10.5281/zenodo.4542661" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">doi.org/10.5281/zenodo.4542661</span><span class="invisible"></span></a></p><p>📒 Codebook - <a href="https://zenodo.org/records/15462956/files/CPP-BT_2025-05-24_Codebook.pdf?download=11" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">zenodo.org/records/15462956/fi</span><span class="invisible">les/CPP-BT_2025-05-24_Codebook.pdf?download=11</span></a></p><p>💻 <a href="https://fediscience.org/tags/RStats" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>RStats</span></a> Source Code - <a href="https://doi.org/10.5281/zenodo.4542665" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">doi.org/10.5281/zenodo.4542665</span><span class="invisible"></span></a></p><p>🔶 Features 🔶 </p><p>+ Insgesamt bis zu 35 Variablen in der CSV-Variante<br>+ Plenarprotokolle von der 1. Wahlperiode bis zur neuesten 21. Wahlperiode am Stichtag<br>+ Aufteilung in Einzelreden u.a. mit ID, Name, Fraktion und Amt der Redner:in (ab 18. Wahlperiode)<br>+ Aufteilung in Protokollbestandteile: Inhaltsverzeichnis, Sitzungsverlauf, Anlagen, Rednerliste (ab 18. Wahlperiode)<br>+ Fortlaufende Aktualisierung (Datensatz kann zusätzlich via Pipeline täglich aktualisiert werden)<br>+ Urheberrechtsfreiheit<br>+ Offene und plattformunabhängige Formate (PDF, TXT, CSV, XML, Parquet)<br>+ Linguistische Kennzahlen<br>+ Umfangreiches Codebook<br>+ Compilation Report, um den Erstellungs-Prozess zu erläutern<br>+ Dutzende Diagramme und Tabellen für alle Zwecke<br>+ Diagramme in einem für den Druck (PDF) und das Web (PNG) optimierten Format<br>+ Kryptographische Signaturen<br>+ Veröffentlichung des Source Codes (Open Source)</p><p><span class="h-card" translate="no"><a href="https://a.gup.pe/u/rstats" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>rstats</span></a></span> <span class="h-card" translate="no"><a href="https://a.gup.pe/u/politicalscience" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>politicalscience</span></a></span> <span class="h-card" translate="no"><a href="https://a.gup.pe/u/histodons" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>histodons</span></a></span> <a href="https://fediscience.org/tags/OpenAccess" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenAccess</span></a> <a href="https://fediscience.org/tags/OpenSource" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenSource</span></a> <a href="https://fediscience.org/tags/OpenScience" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>OpenScience</span></a> <a href="https://fediscience.org/tags/Parliament" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Parliament</span></a> <a href="https://fediscience.org/tags/Bundestag" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Bundestag</span></a> <a href="https://fediscience.org/tags/Plenarprotokoll" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Plenarprotokoll</span></a> <a href="https://fediscience.org/tags/Histodons" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Histodons</span></a> <a href="https://fediscience.org/tags/HistodonsDE" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>HistodonsDE</span></a> <a href="https://fediscience.org/tags/NLP" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>NLP</span></a> <a href="https://fediscience.org/tags/Dataviz" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Dataviz</span></a> <a href="https://fediscience.org/tags/Legislative" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Legislative</span></a> <a href="https://fediscience.org/tags/Debate" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Debate</span></a></p>
Rafael Perez<p>Linguist Noam Chomsky is interviewed by Common Dreams writer C.J. Polychroniou on the subject of ChatGPT in this May 2023 piece. Chomsky's stance on LLMs is that as long as we're not able to atomically understand what goes on in the statistical black box that currently is an LLM, linguists won't be able to benefit from being able to see whether it learns language like a human does, or not.</p><p>"Noam Chomsky Speaks on What ChatGPT Is Really Good For"</p><p><a href="https://chomsky.info/20230503-2/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="">chomsky.info/20230503-2/</span><span class="invisible"></span></a></p><p><a href="https://mastodon.social/tags/chomsky" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>chomsky</span></a> <a href="https://mastodon.social/tags/nlp" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>nlp</span></a> <a href="https://mastodon.social/tags/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>llm</span></a> <a href="https://mastodon.social/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ai</span></a></p>
ExploreLive feeds
About