Popular GitHub Repositories for Sentence Classification

高质量中文预训练模型集合：最先进大模型、最快小模型、相似度专门模型

About Muti-Label Text Classification Based on Neural Network.

Opensource Korean chatbot framework

Classify Kaggle Consumer Finance Complaints into 11 classes. Build the model with CNN (Convolutional Neural Network) and Word Embeddings on Tensorflow.

The code for our paper "NSP-BERT: A Prompt-based Zero-Shot Learner Through an Original Pre-training Task —— Next Sentence Prediction"

About Text Pairs (Sentence Level) Classification (Similarity Modeling) Based on Neural Network.

Extracting scientific claims from biomedical abstracts (powered by AllenNLP)

CNN for intent classification task in a Chatbot

Augmenting word embeddings with their surrounding context using bidirectional RNN

Tensorflow Implementation of Densely Connected Bidirectional LSTM with Applications to Sentence Classification

reference pytorch code for intent classification

Multi Class Text (Feedback) Classification using CNN, GRU Network and pre trained Word2Vec embedding, word embeddings on TensorFlow.

Pytorch implementation of the paper Convolutional Neural Networks for Sentence Classification

This is a Pytorch (+ Huggingface transformers) implementation of a "simple" text classifier defined using BERT-based models. In this lab we will see how it is simple to use BERT for a sentence classification task, obtaining state-of-the-art results in few lines of python code.

CNNs for Classification in PyTorch

KAREN: Unifying Hatespeech Detection and Benchmarking

A general text classifier based on BERT. Multi-process data processing, multi-gpu parallel training, rich monitoring indicators.

Convolution Neural Network for classification of semantic relations in a sentence

EigenSent: Spectral sentence embeddings using higher-order Dynamic Mode Decomposition

Official Contribution for DeftEval 2020, Task 6 Subtask 1 from SemEval 2020 Competition. Solving NLP problem of "extracting term-definition pairs in free text" in multiple approaches ranging from highly simple till very complex modern ones.