Question for the digital humanities people:

Is there any good #OpenSource graphical tool for natural language processing that is both easy to use and performs a reasonable number of analyses?

I am looking for something that the average lawyer or student with a couple of weeks training could operate.

Thanks!

Gradient norms rise at the end of training, and a new theory connects that to the learning loss when using weight decay.
AdamC and SGDC(orrected) multiply the weight decay by the learning rate and fix it.
https://alphaxiv.org/pdf/2506.02285

#ai #ml #llm #pretraining #nlp

Bob Coecke: "Lambek vs Lambek"

https://www.youtube.com/watch?v=0SNB4tLah0Q

The sound is not super good, but the video is nice for an overview of diagram language and applications

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 #InformationRetrieval pipeline running?

Check out Rankify, developed by Abdelrahman Abdallah from the #DataScience Group @uniinnsbruck, which provides an all-in-one retrieval, re-ranking, and retrieval-augmented generation toolkit: https://www.doi.org/10.48763/000013

The 2nd NSLP 2025 Workshop is now underway at #ESWC2025!
Room 3 – Aurora III, Floor 0

NSLP brings together researchers focused on the processing, analysis, transformation, and utilization of scientific language and Research Knowledge Graphs (RKGs).

From papers to structured knowledge — this is where AI meets scientific publishing.

Last week, we continued our #ISE2025 lecture on distributional semantics with the introduction of neural language models (NLMs) and compared them to traditional statistical n-gram models.
Benefits of NLMs:
- Capturing Long-Range Dependencies
- Computational and Statistical Tractability
- Improved Generalisation
- Higher Accuracy

@fiz_karlsruhe @fizise @tabea @sourisnumerique @enorouzi #llms #nlp #AI #lecture

NEU

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.

Auch Einzelreden mit Name, ID und Fraktion der Redner:in!

Download

Datensatz - https://doi.org/10.5281/zenodo.4542661

Codebook - https://zenodo.org/records/15462956/files/CPP-BT_2025-05-24_Codebook.pdf?download=11

#RStats Source Code - https://doi.org/10.5281/zenodo.4542665

Features

+ Insgesamt bis zu 35 Variablen in der CSV-Variante
+ Plenarprotokolle von der 1. Wahlperiode bis zur neuesten 21. Wahlperiode am Stichtag
+ Aufteilung in Einzelreden u.a. mit ID, Name, Fraktion und Amt der Redner:in (ab 18. Wahlperiode)
+ Aufteilung in Protokollbestandteile: Inhaltsverzeichnis, Sitzungsverlauf, Anlagen, Rednerliste (ab 18. Wahlperiode)
+ Fortlaufende Aktualisierung (Datensatz kann zusätzlich via Pipeline täglich aktualisiert werden)
+ Urheberrechtsfreiheit
+ Offene und plattformunabhängige Formate (PDF, TXT, CSV, XML, Parquet)
+ Linguistische Kennzahlen
+ Umfangreiches Codebook
+ Compilation Report, um den Erstellungs-Prozess zu erläutern
+ Dutzende Diagramme und Tabellen für alle Zwecke
+ Diagramme in einem für den Druck (PDF) und das Web (PNG) optimierten Format
+ Kryptographische Signaturen
+ Veröffentlichung des Source Codes (Open Source)

@rstats @politicalscience @histodons #OpenAccess #OpenSource #OpenScience #Parliament #Bundestag #Plenarprotokoll #Histodons #HistodonsDE #NLP #Dataviz #Legislative #Debate

Authors Are Accidentally Leaving AI Prompts In their Novels https://www.404media.co/authors-are-accidentally-leaving-ai-prompts-in-their-novels/

In the #ISE2025 lecture today we were introducing our students to the concept of distributional semantics as the foundation of modern large language models. Historically, Wittgenstein was one of the important figures in the Philosophy of Language stating thet "The meaning of a word is its use in the language."

https://static1.squarespace.com/static/54889e73e4b0a2c1f9891289/t/564b61a4e4b04eca59c4d232/1447780772744/Ludwig.Wittgenstein.-.Philosophical.Investigations.pdf

#philosophy #wittgenstein #nlp #AI #llm #languagemodel #language #lecture @fiz_karlsruhe @fizise @tabea @enorouzi @sourisnumerique #AIart

"The pilot employs state-of-the-art methodologies in the responsible deployment of LLM technology, including:

Multi-step reasoning processes at inference time
Web search capabilities as tools in the reasoning chain
Rigorous checks for proper data source attribution
Comprehensive monitoring and evaluation of LLM contributions
"

#AAAI Launches AI-Powered #PeerReview Assessment System
https://aaai.org/aaai-launches-ai-powered-peer-review-assessment-system/

We present & discuss the new beta #EduTopics app ( https://dipf-lis.shinyapps.io/EduTopicsECER/) at the Workshops »Text Mining in der Erziehungswissenschaft« (@bbf_dipfberlin @dipf_aktuell) which allows you to interactively analyze more than 30,000 #ECER conference abstracts @FachportalPaedagogik #EduSci #nlp #eduresearch @alexchrist @j_roeschlein #EERA_NW12 #OpenResearchInEducation #EduSci #openscience #TopicModeling

Dear registered students for ISWS 2025, please keep in mind that the deadline for the poster submission is not far away...
We are looking forward to your submissions!

#isws2025 #summerschool #semanticweb #semweb #llm #nlp #knowledgegraph #AI #responsibleAI #reliableAI @sourisnumerique @lysander07

Generating Shakespeare-like text with an n-gram language model is straight forward and quite simple. But, don't expect to much of it. It will not be able to recreate a lost Shakespear play for you ;-) It's merely a parrot, making up well sounding sentences out of fragments of original Shakespeare texts...

#ise2025 #lecture #nlp #llm #languagemodel @fiz_karlsruhe @fizise @tabea @enorouzi @sourisnumerique #shakespeare #generativeAI #statistics

In our #ISE2025 lecture last Wednesday, we learned how in n-gram language models via Markov assumption and maximum likelihood estimation we can predict the probability of the occurrence of a word given a specific context (i.e. n words previous in the sequence of words).

#NLP #languagemodels #lecture @fizise @tabea @enorouzi @sourisnumerique @fiz_karlsruhe @KIT_Karlsruhe

help me out #NLP ers: who posted about writing (generating) a decent scientific paper in about 15 hours?
Is there a good open source version?

Reduce human errors in data processing! (Un)Perplexed Spready's AI functions perform consistent, accurate analysis every time -no more mistakes from manual data handling, formula errors, or oversight. Improve data quality while saving time. Precision meets efficiency!
https://matasoft.hr/qtrendcontrol/index.php/un-perplexed-spready

This week, we were discussing the central question Can we "predict" a word? as the basis for statistical language models in our #ISE2025 lecture. Of course, I wasx trying Shakespeare quotes to motivate the (international) students to complement the quotes with "predicted" missing words ;-)

"All the world's a stage, and all the men and women merely...."

#nlp #llms #languagemodel #Shakespeare #AIart lecture @fiz_karlsruhe @fizise @tabea @enorouzi @sourisnumerique #brushUpYourShakespeare

Last week, our students learned how to conduct a proper evaluation for an NLP experiment. To this end, we introduced a small textcorpus with sentences about Joseph Fourier, who counts as one of the discoverers of the greenhouse effect, responsible for global warming.

https://github.com/ISE-FIZKarlsruhe/ISE-teaching/blob/b72690d38911b37748082256b61f96cf86171ace/materials/dataset/fouriercorpus.txt

#ise2025 #nlp #lecture #climatechange #globalwarming #historyofscience #climate @fiz_karlsruhe @fizise @tabea @enorouzi @sourisnumerique