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

Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable.

Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning

Dyalog-apl-docset - Dyalog APL Dash Docset Generator

Unsupervised Representation Learning via Neural Activation Coding

[CVPR 2022] TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing

Code for our method RePRI for Few-Shot Segmentation. Paper at http://arxiv.org/abs/2012.06166

Efficient Sparse Attacks on Videos using Reinforcement Learning

[CVPR2021] Look before you leap: learning landmark features for one-stage visual grounding.

Voice control for Garry's Mod

Simple PyTorch hierarchical models.

A web porting for NVlabs' StyleGAN2, to facilitate exploring all kinds characteristic of StyleGAN networks

Gesture Volume Control v.2

PGPortfolio: Policy Gradient Portfolio, the source code of "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem"(https://arxiv.org/pdf/1706.10059.pdf).

Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation

Source code for "OmniPhotos: Casual 360° VR Photography"

USAD - UnSupervised Anomaly Detection on multivariate time series

Scribble-Supervised LiDAR Semantic Segmentation, CVPR 2022 (ORAL)

[NeurIPS 2021] ORL: Unsupervised Object-Level Representation Learning from Scene Images

DeepSpamReview: Detection of Fake Reviews on Online Review Platforms using Deep Learning Architectures. Summer Internship project at CoreView Systems.

Modular Gaussian Processes