Provenance-first extractive RAG: return verbatim source spans with citations using local ModernBERT or optional LLM-assisted extraction.

Span-level grounding verification for RAG, code, and tool-grounded AI outputs.

Curated list of open-access/open-source/off-the-shelf resources and tools developed with a particular focus on German

XAI based human-in-the-loop framework for automatic rule-learning.

A Typed Event-Focused Lexical Inference Benchmark for Evaluating Natural Language Inference

Resources, datasets, papers on Question Answering

Fixes mojibake and other glitches in Unicode text, after the fact.

A pure python learner of weighted finite state automata

An NLTK-based parser using KR-style morphological annotation

a sequential tagger for NLP using Maximum Entropy Learning and Hidden Markov Models