Paraphrastic Representations at Scale

Code to train models from "Paraphrastic Representations at Scale".

The code is written in Python 3.7 and requires H5py, jieba, numpy, scipy, sentencepiece, sacremoses, and PyTorch >= 1.0 libraries. These can be insalled with the following command:

pip install -r requirements.txt

To get started, download the data files used for training from http://www.cs.cmu.edu/~jwieting and download the STS evaluation data:

wget http://phontron.com/data/paraphrase-at-scale.zip
unzip paraphrase-at-scale.zip
rm paraphrase-at-scale.zip
wget http://www.cs.cmu.edu/~jwieting/STS.zip .
unzip STS.zip
rm STS.zip

If you use our code, models, or data for your work please cite:

@article{wieting2021paraphrastic,
    title={Paraphrastic Representations at Scale},
    author={Wieting, John and Gimpel, Kevin and Neubig, Graham and Berg-Kirkpatrick, Taylor},
    journal={arXiv preprint arXiv:2104.15114},
    year={2021}
}

@inproceedings{wieting19simple,
    title={Simple and Effective Paraphrastic Similarity from Parallel Translations},
    author={Wieting, John and Gimpel, Kevin and Neubig, Graham and Berg-Kirkpatrick, Taylor},
    booktitle={Proceedings of the Association for Computational Linguistics},
    url={https://arxiv.org/abs/1909.13872},
    year={2019}
}

To embed a list of sentences:

python -u embed_sentences.py --sentence-file paraphrase-at-scale/example-sentences.txt --load-file paraphrase-at-scale/model.para.lc.100.pt  --sp-model paraphrase-at-scale/paranmt.model --output-file sentence_embeds.np --gpu 0

To score a list of sentence pairs:

python -u score_sentence_pairs.py --sentence-pair-file paraphrase-at-scale/example-sentences-pairs.txt --load-file paraphrase-at-scale/model.para.lc.100.pt  --sp-model paraphrase-at-scale/paranmt.model --gpu 0

To train a model (for example, on ParaNMT):

python -u main.py --outfile model.para.out --lower-case 1 --tokenize 0 --data-file paraphrase-at-scale/paranmt.sim-low=0.4-sim-high=1.0-ovl=0.7.final.h5 \
       --model avg --dim 1024 --epochs 25 --dropout 0.0 --sp-model paraphrase-at-scale/paranmt.model --megabatch-size 100 --save-every-epoch 1 --gpu 0 --vocab-file paraphrase-at-scale/paranmt.sim-low=0.4-sim-high=1.0-ovl=0.7.final.vocab

To download and preprocess raw data for training models (both bilingual and ParaNMT), see preprocess/bilingual and preprocess/paranmt.

Code to train models from "Paraphrastic Representations at Scale".

Related tags

Overview

Paraphrastic Representations at Scale

Owner

John Wieting

PaSST: Efficient Training of Audio Transformers with Patchout

The aim of the game, as in the original one, is to find a specific image from a group of different images of a person's face

Code release for "MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound"

GDSC-ML Team Interview Task

STBP is a way to train SNN with datasets by Backward propagation.

git《Tangent Space Backpropogation for 3D Transformation Groups》(CVPR 2021) GitHub:1]

Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners

Python interface for the DIGIT tactile sensor

TeachMyAgent is a testbed platform for Automatic Curriculum Learning methods in Deep RL.

This is the codebase for Diffusion Models Beat GANS on Image Synthesis.

Code for "Localization with Sampling-Argmax", NeurIPS 2021

Transparent Transformer Segmentation

A multi-entity Transformer for multi-agent spatiotemporal modeling.

This project aims to explore the deployment of Swin-Transformer based on TensorRT, including the test results of FP16 and INT8.

Official code repository for the publication "Latent Equilibrium: A unified learning theory for arbitrarily fast computation with arbitrarily slow neurons"

Bottleneck Transformers for Visual Recognition

[NeurIPS 2021] Low-Rank Subspaces in GANs

Depth-Aware Video Frame Interpolation (CVPR 2019)

Pytorch implementation of the paper: "A Unified Framework for Separating Superimposed Images", in CVPR 2020.

Semantic Image Synthesis with SPADE