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

thundernet ncnn

Performance Analysis of Multi-user NOMA Wireless-Powered mMTC Networks: A Stochastic Geometry Approach

Trafffic prediction analysis using hybrid models - Machine Learning

VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning

Message Passing on Cell Complexes

Neighborhood Reconstructing Autoencoders

ROMP: Monocular, One-stage, Regression of Multiple 3D People, ICCV21

A repo for Causal Imitation Learning under Temporally Correlated Noise

領域を指定し、キーを入力することで画像を保存するツールです。クラス分類用のデータセット作成を想定しています。

A python script to convert images to animated sus among us crewmate twerk jifs as seen on r/196

Meta Language-Specific Layers in Multilingual Language Models

PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility

SmallInitEmb - LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence

A repository for the updated version of CoinRun used to collect MUGEN, a multimodal video-audio-text dataset.

LTR_CrossEncoder: Legal Text Retrieval Zalo AI Challenge 2021

Fast (simple) spectral synthesis and emission-line fitting of DESI spectra.

This repo contains the source code and a benchmark for predicting user's utilities with Machine Learning techniques for Computational Persuasion

Vector Neurons: A General Framework for SO(3)-Equivariant Networks

RRxIO - Robust Radar Visual/Thermal Inertial Odometry: Robust and accurate state estimation even in challenging visual conditions.

Deep learning (neural network) based remote photoplethysmography: how to extract pulse signal from video using deep learning tools