University of Surrey - NLP

All

22 repositories

ALOPE
Public
[COLM2025] Repository contains codebase for "ALOPE" framework which can help train efficient LoRA adapters for Quality Estimation of Machine Translated Text
Python
•0•0•0•0•Updated Aug 28, 2025Aug 28, 2025
NLP-2025
Public
Labs for COM3029/COMM061 at University of Surrey
natural-language-processing deep-learning transformers large-language-models
Jupyter Notebook
•
MIT License
•6•1•0•0•Updated May 6, 2025May 6, 2025
homo_gen
Public
This repository contains the code and data to generate Chinese homophone words to probe machine translation evaluation systems or avoid media censorship.
Python
•
Creative Commons Attribution Share Alike 4.0 International
•0•0•0•0•Updated Mar 21, 2025Mar 21, 2025
Video-vs-Meme-Hate
Public
Python
•
MIT License
•0•1•0•0•Updated Feb 28, 2025Feb 28, 2025
COLING-Tutorial-LowResScene-2025
Public
Code Repository for the tutorial "Connecting Ideas in Lower-Resource Scenarios: NLP for National Varieties, Creoles, and Other Low-resource Languages @ COLING 2025
Jupyter Notebook
•0•7•0•0•Updated Jan 20, 2025Jan 20, 2025
HADQAET
Public
This repository contains the dataset for our paper "Evaluation of Chinese-English Machine Translation of Emotion-Loaded Microblog Texts: A Human Annotated Dataset for the Quality Assessment of Emotion Translation"
translation-quality-estimation emotion-transfer chinese-english-translation
0•1•0•0•Updated Nov 17, 2024Nov 17, 2024
LLMs4MTQE-UGC
Public
This repository contains the code and data for LLMs to evaluate machine translation of emotion-loaded Chinese user-generated content (UGC).
user-generated-content llms machine-translation-evaluation
0•0•0•0•Updated Nov 11, 2024Nov 11, 2024
LLM4MT_eval
Public
This repository is for our paper "What do large language model need for machine translation evaluation?"
machine-translation translation-evaluation large-language-models
Python
•
Creative Commons Attribution Share Alike 4.0 International
•1•4•0•0•Updated Nov 11, 2024Nov 11, 2024
MTL4QE
Public
This repository contains the code and data to train multi-task learning (MTL) models to evaluate machine translation of emotion-loaded user-generated content (UGC).
multitask-learning translation-quality-estimation
Python
•
Creative Commons Attribution Share Alike 4.0 International
•0•0•0•0•Updated Nov 11, 2024Nov 11, 2024
AMTA-EditDistances-tutorial
Public
This repository contains the code and resources for our tutorial presented at AMTA 2024.
Jupyter Notebook
•1•0•0•0•Updated Sep 20, 2024Sep 20, 2024
PLODv2-CLM4AbbrDetection
Public
This repository contains the code and PLODv2 dataset to train character-level language models (CLM) for abbreviation and long-form detection released with our LREC-COLING 2024 publication
natural-language-processing datasets sequence-labeling character-level-language-model abbreviations-detection
Jupyter Notebook
•
Creative Commons Attribution Share Alike 4.0 International
•0•0•0•0•Updated May 30, 2024May 30, 2024
NLP-2024
Public
This lab module is in correspondence to the theory course module for Natural Language Processing (2024)
Jupyter Notebook
•6•10•0•0•Updated May 6, 2024May 6, 2024
Linking-Judgements
Public
0•0•0•0•Updated Mar 25, 2024Mar 25, 2024
woah-aggression-detection
Public
This repository contains resources for aggression and offensive language detection, for our WOAH 2023 publication.
aggression-detection offensive-language-detection
Python
•1•2•0•0•Updated Jun 30, 2023Jun 30, 2023
IndicQE-PE
Public
This repository contains Quality Estimation and Automatic Post-editing datasets for Indian languages created with the help of SurreyNLP.
0•0•0•0•Updated May 26, 2023May 26, 2023
NLP-2023
Public
Jupyter Notebook
•12•7•0•0•Updated May 10, 2023May 10, 2023
S3D
Public
This repository contains our sarcasm annotated datasets along with notebooks to use our fine-tuned language models for our EMNLP 2022 Workshop Paper: "Utilizing Weak Supervision to Create S3D: A Sarcasm Annotated Dataset"
deep-learning sentiment-analysis sarcasm-detection nlp machine-learning natural-language-processing dataset
Jupyter Notebook
•
Creative Commons Attribution Share Alike 4.0 International
•1•7•0•0•Updated Jan 21, 2023Jan 21, 2023
political-aggression-detection
Public
Code for WASSA submission, 2023
natural-language-processing aggression-detection
HTML
•0•0•0•0•Updated Jan 13, 2023Jan 13, 2023
PLOD-AbbreviationDetection
Public
This repository contains the PLOD Dataset for Abbreviation Detection released with our LREC 2022 publication
transformers pytorch dataset tensorflow2 abbreviations-detection acronym-identification nlp machine-learning natural-language-processing spacy
Jupyter Notebook
•
Creative Commons Attribution Share Alike 4.0 International
•4•12•0•0•Updated Sep 25, 2022Sep 25, 2022
Local-NMT
Public
Host and Inference via pre-trained NMT models
translation machine-translation transformer flask-application neural-machine-translation nmt
CSS
•
Creative Commons Attribution Share Alike 4.0 International
•9•0•0•0•Updated Aug 19, 2022Aug 19, 2022
APE-Shared-Task
Public
This repository contains the Automatic Post Editing shared task data for the English-Marathi language pair.
Mathematica
•1•3•0•0•Updated May 19, 2022May 19, 2022
qe-evaluation
Public
Adversarial Evaluation of Quality Estimation systems
quality-estimation
Jupyter Notebook
•
Creative Commons Attribution Share Alike 4.0 International
•0•7•0•0•Updated Apr 18, 2022Apr 18, 2022