There are 0 repository under siamese-lstm topic.
Implementation of Siamese Neural Networks built upon multihead attention mechanism for text semantic similarity task.
Solution to Kaggle's Quora Duplicate Question Detection Competition
Siamese-LSTM PyTorch Implementation for cikm 2018
A Keras Implementation of Attention_based Siamese Manhattan LSTM
Keras implementation (tensorflow backend) of natural language inference
A Mention-Ranking Model for Abstract Anaphora Resolution
Deep-learning model presented in "DataStories at SemEval-2017 Task 6: Siamese LSTM with Attention for Humorous Text Comparison".
Three models are implemented for text similarity classification/STS problem on Quora Question Pairs dataset.
Text Classification Using Siamese Neural Networks - Contrastive Loss, Triplet Loss. This architecture works well when the training data is less.
Siamese LSTM and Bert Transformers for evaluating similarity between sentences of the Quora Question Pairs Dataset.
Theano implementation of siamese LSTMs for evaluating semantic similarity between sentences.
This repositpory entails an implementation of a Deep Learning Pipeline that can be used to evaulate the semantic similarity of two sentenences using Siamese LSTM Neural Network.
Anomaly Classification in Time Series Data
Text Classification using Few-Shot Learning with few labeled examples.
Bachelor Thesis Project
This repository contains keras implementation of the paper Learning Sentence Similarity with Siamese Recurrent Architectures
An attempt at https://www.kaggle.com/c/quora-question-pairs
Detecting Quora duplicate questions using a Siamese LSTM.
The Facenet paper of 2015 proposed an interesting solution for huge multiclass problems. Instead of the traditional approach, we try to learn a similarity function i.e. degree of difference between 2 inputs. If the degree of difference between the inputs is less than a threshold then the inputs are classified as similar else different.
Exploratory data anlaysis and machine learning modelling detecting for duplicate question pairs.