tollefj
phd candidate/computer "scientist". summarization, embeddings, coreference++ for low-resource languages.
Norwegian University of Science and TechnologyNorway
Pinned Repositories
10K-Sentiment
Download 10-K reports and run through sentiment analysis.
ClEval
CL-Eval framework used in my master's thesis on Coreference Resolution and Sentiment Analysis
coreference-eval
A module for evaluation of coreference chains (in an array/jsonlike format), using common metrics for coreference resolution
FileGrabberNTNU
Automatically download all files contained in your itslearning account. Made due to the move to blackboard as of july 15.
formula-student-practice-quiz
Quiz for FSA/G practice
information-retrieval
Information Retrieval course, fall 2017.
intro-ai
Introduction to artificial intelligence course, fall 2017.
KriRAG-develop
Continued development of the system for the paper "Enhancing Criminal Investigation Analysis with Summarization and Memory-based Retrieval-Augmented Generation: A Comprehensive Evaluation of Real Case Data"
TDT4310
Course page for TDT4310 Intelligent Text Analytics and Language Understanding, spring 2024.
whisper-subtitler
A simple one-command subtitle transcriber for input audio and video using whisper models.
tollefj's Repositories
tollefj/TDT4310
Course page for TDT4310 Intelligent Text Analytics and Language Understanding, spring 2024.
tollefj/coreference-eval
A module for evaluation of coreference chains (in an array/jsonlike format), using common metrics for coreference resolution
tollefj/KriRAG-develop
Continued development of the system for the paper "Enhancing Criminal Investigation Analysis with Summarization and Memory-based Retrieval-Augmented Generation: A Comprehensive Evaluation of Real Case Data"
tollefj/nordavind
tollefj/UD-NARC
conversion and merging of NARC and UD
tollefj/WebScrapers
A collection of web scrapers
tollefj/dotfiles
Various dotfiles. MORE DOTS!
tollefj/SemRel-2024
tollefj/whisper-subtitler
A simple one-command subtitle transcriber for input audio and video using whisper models.
tollefj/asr-demos
tollefj/augmented-pair-encoder
A lightweight sentence-pair encoder for similarity tasks. Includes a data augmentation pipeline from sentence-transformers.
tollefj/brage_2025
Code repo for the paper: The BRAGE Benchmark: Evaluating Zero-shot Learning Capabilities of Large Language Models for Norwegian Customer Service Dialogues
tollefj/CLSC
Code for the paper "Cross-Lingual Sentence Compression for Length-Constrained Subtitles in Low-Resource Settings"
tollefj/CorefUD-baseline
A baseline for CorefUD
tollefj/get-params
this package allows you to fetch the arguments of a function from a simple search string, matching a function within a module.
tollefj/KriRAG
tollefj/llama-cpp-python-server
A simple inference server for llama cpp python, based on prompt configurations and more.
tollefj/margins-contrastive
Code for the paper: "Margins in Contrastive Learning: Evaluating Multi-task Retrieval for Sentence Embeddings"
tollefj/mathea-oscar
tollefj/nocola
Official repository for NoCoLA dataset
tollefj/nor-llm-things
Some llm examples for Norwegian
tollefj/norne
Norwegian Named Entities annotations on top of NDT (Norwegian Dependency Treebank)
tollefj/norwegian-criminal-sts
Advancing Knowledge Discoveries in Criminal Investigations with Semantic Textual Similarity
tollefj/public_html
my ntnu homepage: https://folk.ntnu.no/tollefj/ mirrored at https://tollefj.github.io/public_html/
tollefj/pyplate
A general-purpose boilerplate for Python projects. Includes task-specific requirements.
tollefj/pyplate-simple
a simplified setup for basic python applications
tollefj/subtitle-compression
tollefj/tollefj
tollefj/tollefj.github.io
tollefj/UNER_Norwegian-NorNE
UNER converted NorNE data