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

(EI 2022) Controllable Confidence-Based Image Denoising

[ICSE2020] MemLock: Memory Usage Guided Fuzzing

Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

Implementation of ToeplitzLDA for spatiotemporal stationary time series data.

Official implementation of UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation

Deep Sketch-guided Cartoon Video Inbetweening

Python implementation of the multistate Bennett acceptance ratio (MBAR)

[ICLR 2021] Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments.

SwinTrack: A Simple and Strong Baseline for Transformer Tracking

Code for Learning Manifold Patch-Based Representations of Man-Made Shapes, in ICLR 2021.

Experiments on continual learning from a stream of pretrained models.

Official Pytorch implementation of "Unbiased Classification Through Bias-Contrastive and Bias-Balanced Learning (NeurIPS 2021)

Tweesent-back - Tweesent backend uses fastAPI as the web framework

Irrigation controller for Home Assistant

IndoNLI: A Natural Language Inference Dataset for Indonesian

An Intelligent Self-driving Truck System For Highway Transportation

External Attention Network

This is an official PyTorch implementation of Task-Adaptive Neural Network Search with Meta-Contrastive Learning (NeurIPS 2021, Spotlight).

Simple tutorials on Pytorch DDP training

Incremental Cross-Domain Adaptation for Robust Retinopathy Screening via Bayesian Deep Learning