This repository provides all the models that we use to solve the Context Independent Claim Detection Argumentation Mining sub-task.

Tag-enhanced Tree-Structured NN for discourse relation classification.

Neural-Network Guided Expression Transformation

THANOS is a modification in HAN (Hierarchical Attention Network) architecture. Here we use Tree LSTM to obtain the embeddings for each sentence.

Head-Lexicalized Bidirectional Tree LSTMs

A Tree-LSTM-based dependency tree sentiment labeler

Tree LSTM implementation in PyTorch

Recursive Neural Networks for PyTorch

Tree Stack Memory Units

Set of PyTorch modules for developing and evaluating different algorithms for embedding trees.

An reimplementation of Makoto Miwa and Mohit Bansa. End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures. http://dx.doi.org/10.18653/v1/P16-1105)

Sentiment analysis using neural BoW and LSTM based models

Kistmat-AI is an advanced machine learning model designed to solve a wide range of mathematical problems, from elementary arithmetic to university-level calculus. This project demonstrates the application of curriculum learning in AI, allowing the model to progressively tackle more complex mathematical concepts.