Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.

Last update: Dec 29, 2022

Related tags

Deep Learning wechsel

Overview

WECHSEL

Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.

arXiv: https://arxiv.org/abs/2112.06598

Models from the paper are available on the HuggingFace Hub:

Installation

We distribute a Python Package via PyPI:

pip install wechsel

Alternatively, clone the repository, install requirements.txt and run the code in wechsel/.

Example usage

Transferring English roberta-base to Swahili:

import torch
from transformers import AutoModel, AutoTokenizer
from datasets import load_dataset
from wechsel import WECHSEL, load_embeddings

source_tokenizer = AutoTokenizer.from_pretrained("roberta-base")
model = AutoModel.from_pretrained("roberta-base")

target_tokenizer = source_tokenizer.train_new_from_iterator(
    load_dataset("oscar", "unshuffled_deduplicated_sw", split="train")["text"],
    vocab_size=len(source_tokenizer)
)

wechsel = WECHSEL(
    load_embeddings("en"),
    load_embeddings("sw"),
    bilingual_dictionary="swahili"
)

target_embeddings, info = wechsel.apply(
    source_tokenizer,
    target_tokenizer,
    model.get_input_embeddings().weight.detach().numpy(),
)

model.get_input_embeddings().weight.data = torch.from_numpy(target_embeddings)

# use `model` and `target_tokenizer` to continue training in Swahili!

Bilingual dictionaries

We distribute 3276 bilingual dictionaries from English to other languages for use with WECHSEL in dicts/.

Citation

Please cite WECHSEL as

@misc{minixhofer2021wechsel,
      title={WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models}, 
      author={Benjamin Minixhofer and Fabian Paischer and Navid Rekabsaz},
      year={2021},
      eprint={2112.06598},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.

Related tags

Overview

WECHSEL

Installation

Example usage

Bilingual dictionaries

Citation

Owner

Institute of Computational Perception

Code for "Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo"

Deep Reinforcement Learning based Trading Agent for Bitcoin

Reference code for the paper "Cross-Camera Convolutional Color Constancy" (ICCV 2021)

Code for Motion Representations for Articulated Animation paper

Code & Data for Enhancing Photorealism Enhancement

This implementation contains the application of GPlearn's symbolic transformer on a commodity futures sector of the financial market.

Baseline of DCASE 2020 task 4

Neighbor2Seq: Deep Learning on Massive Graphs by Transforming Neighbors to Sequences

Public repository containing materials used for Feed Forward (FF) Neural Networks article.

A pytorch-based deep learning framework for multi-modal 2D/3D medical image segmentation

Simple-Neural-Network From Scratch in Python

LIVECell - A large-scale dataset for label-free live cell segmentation

TeST: Temporal-Stable Thresholding for Semi-supervised Learning

Attention-based Transformation from Latent Features to Point Clouds (AAAI 2022)

Pseudo-rng-app - whos needs science to make a random number when you have pseudoscience?

Credit fraud detection in Python using a Jupyter Notebook

Code for our paper "Multi-scale Guided Attention for Medical Image Segmentation"

Official implementation of Deep Convolutional Dictionary Learning for Image Denoising.

PyTorch implementation of the wavelet analysis from Torrence & Compo

This is a repo of basic Machine Learning!