COLING2018

Sentence Embedder

Provides training and testing code for a CNN-based sentence embedding model

Python code for training and testing the model in the COLING 2018 paper: "Convolutional Neural Network for Universal Sentence Embeddings". This simple CNN model achieves strong performance on semantic similarity tasks in transfer learning setting, and it can also act as effective initialization for downstream tasks.

GitHub

2 stars
0 watching
2 forks
Language: Python
last commit: over 6 years ago

Related projects:

Repository Description Stars
jwieting/iclr2016 Code for training universal paraphrastic sentence embeddings and models on semantic similarity tasks 193
lajanugen/s2v An implementation of a neural network model for learning efficient sentence representations from text data. 205
zhegan27/convsent Trains an autoencoder to learn generic sentence representations using convolutional neural networks 34
jwieting/acl2017 A codebase for training and using models of sentence embeddings. 33
wangyuxinwhy/uniem Develops unified sentence embedding models for NLP tasks 833
malllabiisc/wordgcn A deep learning model that generates word embeddings by predicting words based on their dependency context 290
zhangxiann/skip-gram A Python implementation of a neural network model for learning word embeddings from text data 6
jwieting/para-nmt-50m A collection of pre-trained models and code for training paraphrastic sentence embeddings from large machine translation datasets. 102
johngiorgi/declutr A tool for training and evaluating sentence embeddings using deep contrastive learning 379
bohanli/bert-flow A TensorFlow implementation of sentence embedding from pre-trained language models 529
jwieting/paragram-word Trains word embeddings from a paraphrase database to represent semantic relationships between words. 30
oborchers/fast_sentence_embeddings A Python library for efficiently computing sentence embeddings from large datasets 618
iarroyof/sentence_embedding A method to convert word embeddings into sentence representations by applying entropy weights calculated from TFIDF transform. 9
princetonml/sif A Python implementation of a sentence embedding algorithm using the Smooth Inverse Frequency weighting scheme 1,083
vzhong/embeddings Provides fast and efficient word embeddings for natural language processing. 223