#NaturalLanguage

☮ ♥ ♬ 🧑‍💻peterrenshaw@ioc.exchange
2025-06-25

#AndrejKarpathy joined us at #AI #StartupSchool on June 17th (2025) with a clear message: #software is changing, again.

He sees a shift underway: we’ve entered the era of “Software 3.0,” where #M
#NaturalLanguage becomes the new #programming interface and #models do the rest. He explores what this shift means for #developers, #users, and the #design of #software itself— that we're not just using new #tools, but building a new kind of computer.”

#YCombinator / #VibeCoding / #WhiteCollar / #ZeroHourWork <youtube.com/watch?v=LCEmiRjPEt>

Wikidata Taiwan 臺灣維基數據社群wikidatatw@liker.social
2025-06-11

我們知道 Wikidata 的資料可以用 SPARQL 語法做出各種不同的查詢方式跟資料呈現方式,但是怎麼樣產出對應的 SPARQL 語法一直都是大家困擾的地方,社群與 Wikidata 團隊也不斷在降低 SPARQL 語法上面持續努力。

《Conversational Lexicography: Querying Lexicographic Data on Knowledge Graphs with SPARQL through Natural Language》這篇論文探討如何讓非專業使用者能夠透過自然語言查詢 Wikidata 中的 Lexeme Data,而不需要直接使用 SPARQL 查詢語言。
研究團隊建立了一個多維分類法,解析 Wikidata Lexeme 的複雜性,並創建了一個包含超過 120 萬筆自然語言與 SPARQL 查詢對應的模板數據集。他們測試了 GPT-2、Phi-1.5 和 GPT-3.5-Turbo,發現 GPT-3.5-Turbo 在泛化能力上表現最佳,顯示模型規模與多樣化預訓練對適應能力至關重要。然而,研究也指出,在處理多樣化語言數據與擴展至完整詞典知識表示方面仍有挑戰。

更多完整資訊可參閱論文頁面:arxiv.org/pdf/2505.19971

#Wikidata #維基資料 #維基數據
#SPQRQL #QueryService #lexeme
#NaturalLanguage #LexicographicData

N-gated Hacker Newsngate
2025-05-17

Ah, yes, the revolutionary idea of "talking" to with natural language, because typing coherent sentences is clearly more efficient than clicking buttons. 🙄 Let's all pretend we're not just wrapping our laziness in a shiny new acronym: MCP! 🚀✨
usetexture.com/##

2025-04-17
Victoria Stuart 🇨🇦 🏳️‍⚧️persagen
2025-04-09
N-gated Hacker Newsngate
2025-04-05

🥳🎉 Oh, rejoice! Another AI tool promising to turn your mundane natural language into magic! 💫 Because, you know, writing "SELECT * FROM table" was *so* 2022. 🙄
query-gpt.com/

2025-03-12

Is there a cognate lookup that doesn’t rely on a base language? There are plenty of multilingual options that force you to select an input or output option. Are there any that search close-enough words (whether cognates or simply spelled similarly)?

@mattia I want to know if these exist too, this is a really, really good idea, to have one that combines all languages.

LLMs are the closest thing we have so far but the accuracy is very low. And really, a tool such as this should be no more complex than a spell checker, and so a lookup should only take up a tiny fraction of the amount of memory and compute power an LLM requires for local inference.

#language #NaturalLanguage #software #SoftwareEngineering

2025-03-05

Google's finally catching up to Perplexity, ChatGPT and Claude.

#AI #GoogleGemini #Google #Multimodal #NaturalLanguage #NLP #Search

======

Google's AI Search Evolution: Reimagining How We Find Information
androidfaithful.com/googles-ai

---
Google's Gemini 2.0 uses advanced reasoning capabilities to understand context and provide more meaningful responses, with key improvements including enhanced performance, multimodal queries, faster response generation, and nuanced understanding of user intent.

Example thumbnail of how Google's AI search will work on mobile and web
2024-11-23

“Potnia: a #Python library for converting ancient texts to #Unicode”. Aw yiss, this is the kind of #PyConAU presentation that I'm here for.

pypi.org/project/potnia/

#NaturalLanguage #Humanities #Linguistics

Colan Schwartzcolanschwartz
2024-10-19

So if the other side's representative is also an AI, we'll have 2 AIs talking to each other. This makes me wonder: Wouldn't human languages be inefficient for them? Why not simply just send a request to their API?
fastcompany.com/91112580/donot

Vivienne Dunstanvivdunstan@mastodon.scot
2024-09-26

Firing up #Inform7 on my #Mac to write another #interactiveFiction #game. Getting stuck into the prologue. This will be a much bigger game than I've written before, including 7 main sections in the #code. It is going to take some time. So best get on with it sooner rather than later! Excited to be back #coding. There's something magical about using this #declarative / #naturalLanguage / #objectOriented #programming language and IDE. #GameDev #IndieGame #TextGames #Parser #TextAdventure #Inform

Simon Lucysimon_lucy
2024-09-18

As one of those that is quite likely to use the word delve in both the original archaic sense of tilling the soil and the more current general sense of doing work and research in some detail, I'm more than a little indignant that its overuse by Openai generators is likely to cast doubt upon my own legitimate vocabulary.

And yes spelt is the past tense of the verb to spell. And yes this is serious.

2024-08-01

Today on hashtag#MapScaping: our very own Jason Gilman dives into the world of #NaturalLanguage Geocoding and discusses the future of ML and AI in geospatial.

We're a little biased, but as far as we're concerned this is a must listen! Check it out, and get in touch with any questions you have for Jason and our team.

Full podcast: mapscaping.com/podcast/natural

You can read more about our work on natural language geocoding (and beyond) anytime on our blog: lnkd.in/drsyDSGV

Client Info

Server: https://mastodon.social
Version: 2025.04
Repository: https://github.com/cyevgeniy/lmst