uds-lsv Goto Github PK
Name: Saarland University Spoken Language Systems Group
Type: Organization
Name: Saarland University Spoken Language Systems Group
Type: Organization
Repository for SocialNLP paper "Exploiting Social Media Content for Self-Supervised Style Transfer".
Code for the paper 'AAdaM at SemEval-2024 Task 1: Augmentation and Adaptation for Multilingual Semantic Textual Relatedness'
ATC-Anno is an annotation tool for Air Traffic Control data that offers automatic semantic and concept annotation.
Data/code for EMNLP 2021 paper: Preventing Author Profiling through Zero-Shot Multilingual Back-Translation
A repo for acoustic word embeddings and phonological similarity
Is BERT Robust to Label Noise? A Study on Learning with Noisy Labels in Text Classification
On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines
Supplementary data for the 2021 JNLE article "Automatic Generation of Lexica for Sentiment Polarity Shifters" by Schulder, Wiegand and Ruppenhofer.
Supplementary data for the IJCNLP 2017 paper "Towards Bootstrapping a Polarity Shifter Lexicon using Linguistic Features" by Schulder, Wiegand, Ruppenhofer and Roth.
Supplementary data for the COLING 2018 paper "Automatically Creating a Lexicon of Verbal Polarity Shifters: Mono- and Cross-lingual Methods for German" by Schulder, Wiegand and Ruppenhofer.
Weaker Than You Think: A Critical Look at Weakly Supervised Learning
Domain Adaptation for Spoken Language ID
This repository contains the dataset created for the LREC 2018 paper "Disambiguation of Verbal Shifters" by Michael Wiegand, Sylvette Loda and Josef Ruppenhofer
Python script for generating random Dyck words.
Molecule Transformers is a collection of recipes for pre-training and fine-tuning molecular transformer language models, including BART, BERT, etc. Full thesis available at https://moleculetransformers.github.io/thesis_cs_msc_Khan_Shahrukh.pdf.
Logit Pairing Methods Can Fool Gradient-Based Attacks [NeurIPS 2018 Workshop on Security in Machine Learning]
This repository contains a system to extract opinion roles from German text. It was implemented in the context of the IGGSA-shared task on Source, Subjective Expression and Target Extraction from Political Speeches.
This repository contains all manually labeled data from the GermEval-2018 shared task.
Hierarchical Universal Modular ANotator
This repository contains the code for the RANLP 19 paper incom.py - A Toolbox for Calculating Linguistic Distances and Asymmetries between Related Languages
A simple toolkit to train and evaluate language models.
This repository contains all new resources that were created for the NAACL-2018 paper "Inducing a Lexicon of Abusive Words -- A Feature-Based Approach" by Michael Wiegand, Josef Ruppenhofer, Anna Schmidt and Clayton Greenberg.
Supplementary data for the LREC 2018 paper "Introducing a Lexicon of Verbal Polarity Shifters for English" by Schulder, Wiegand, Ruppenhofer and Köser.
Supplementary data for the LREC 2020 paper "Enhancing a Lexicon of Polarity Shifters through the Automatic Addition of Shifting Directions" by Schulder, Wiegand and Ruppenhofer.
Fine-tuning large language models with huggingface transformers and deepspeed
NAACL 2022: MCSE: Multimodal Contrastive Learning of Sentence Embeddings
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.