malt-iro
Master's degree student at the University of Konstanz, specializing in Computational Linguistics and NLP. 👩‍💻 Interested about LLMs & Text Simplification.
University of KonstanzKonstanz
Pinned Repositories
text-simplification-bot
A simple bot for simplifying texts using language models.
Data_Analysis_R
In this project, I utilized R to perform a comprehensive data analysis on linguistic data characterized by categorical labels, specifically binary values. Additionally, I developed a predictive model to forecast these binary outcomes by assessing the significance of various predictors extracted from the dataset.
document2slides
This repository contains the code to reconstruct the training dataset from NLP/ML Papers in PDF format together with their corresponding slides.
Emotions_classification_DeepLearning
The aim of this project is to build a multi-class classification model which is trained on tweets that convey one of the following emotions: joy, sadness, anger or fear. The task is also a single-label classification since each sample requires one label (emotion). Final conclusions are reported in the jupyter notebook file.
LENS
malt-iro
Positive_Pointwise_Mutual_Information_Python
Analyzed word co-occurrences in the Contemporary American English corpus, showing that PPMI scores are more reliable for identifying collocates and named entities (e.g., “pay attention”, “New York”) compared to simple bigram counts.
SAL_NLP_project
The primary goal of this project is to examine whether the extracted and encoded Tamil multi-word tokens exhibit greater semantic similarity to their respective translations in English or in German. This similarity will be assessed using cosine similarity as a metric.
malt-iro's Repositories
malt-iro/Emotions_classification_DeepLearning
The aim of this project is to build a multi-class classification model which is trained on tweets that convey one of the following emotions: joy, sadness, anger or fear. The task is also a single-label classification since each sample requires one label (emotion). Final conclusions are reported in the jupyter notebook file.
malt-iro/Positive_Pointwise_Mutual_Information_Python
Analyzed word co-occurrences in the Contemporary American English corpus, showing that PPMI scores are more reliable for identifying collocates and named entities (e.g., “pay attention”, “New York”) compared to simple bigram counts.
malt-iro/Data_Analysis_R
In this project, I utilized R to perform a comprehensive data analysis on linguistic data characterized by categorical labels, specifically binary values. Additionally, I developed a predictive model to forecast these binary outcomes by assessing the significance of various predictors extracted from the dataset.
malt-iro/document2slides
This repository contains the code to reconstruct the training dataset from NLP/ML Papers in PDF format together with their corresponding slides.
malt-iro/LENS
malt-iro/malt-iro
malt-iro/SAL_NLP_project
The primary goal of this project is to examine whether the extracted and encoded Tamil multi-word tokens exhibit greater semantic similarity to their respective translations in English or in German. This similarity will be assessed using cosine similarity as a metric.