BiMPM: Bilateral Multi-Perspective Matching for Natural Language Sentences

Various models and code (Manhattan LSTM, Siamese LSTM + Matching Layer, BiMPM) for the paraphrase identification task, specifically with the Quora Question Pairs dataset.

Neural network toolkit for sentence pair modeling.

Implementation of Siamese Neural Networks built upon multihead attention mechanism for text semantic similarity task.

This is our team's solution report, which achieves top 10% (305/3307) in this competition.

Code for paper title "Learning Semantic Sentence Embeddings using Pair-wise Discriminator" COLING-2018

Large scale sentential paraphrases collection and annotation

Heterogenous, Task- and Domain-Specific Benchmark for Unsupervised Sentence Embeddings used in the TSDAE paper: https://arxiv.org/abs/2104.06979.

Variants of Multi-Perspective Convolutional Neural Networks

Paraphrase question identification using Feature Fusion Network (FFN).

Paraphrase Generation Using Deep Reinforcement Learning - MSc Thesis

Source code for SDM 2020 paper "What Do Questions Exactly Ask? MFAE: Duplicate Question Identification with Multi-Fusion Asking Emphasis"

Paraphrase Identification with Deep Learning using Keras

Matching The Statements: A Simple and Accurate Model for Key Point Analysis (ArgMining | EMNLP 2021)

Official Repository for the paper titled "Meta-Learning for Effective Multi-task and Multilingual Modelling" accepted at EACL 2021

Paraphase Generation

Large Scale Multilingual Paraphrase Corpus

bachelors thesis