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

Spontaneous Facial Micro Expression Recognition using 3D Spatio-Temporal Convolutional Neural Networks

Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework

Keras implementation of Normalizer-Free Networks and SGD - Adaptive Gradient Clipping

Ranger deep learning optimizer rewrite to use newest components

Open-source python package for the extraction of Radiomics features from 2D and 3D images and binary masks.

a Lightweight library for sequential learning agents, including reinforcement learning

Implementation of fast algorithms for Maximum Spanning Tree (MST) parsing that includes fast ArcMax+Reweighting+Tarjan algorithm for single-root dependency parsing.

Transfer Reinforcement Learning for Differing Action Spaces via Q-Network Representations

ncnn is a high-performance neural network inference framework optimized for the mobile platform

ICCV2021 Oral SA-ConvONet: Sign-Agnostic Optimization of Convolutional Occupancy Networks

Code associated with the paper "Towards Understanding the Data Dependency of Mixup-style Training".

Repo for paper "Dynamic Placement of Rapidly Deployable Mobile Sensor Robots Using Machine Learning and Expected Value of Information"

The audio-video synchronization of MKV Container Format is exploited to achieve data hiding

Phy-Q: A Benchmark for Physical Reasoning

Simple embedding based text classifier inspired by fastText, implemented in tensorflow

PyTorch implementation of paper "StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement" (ICCV 2021 Oral)

Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting

auto-tuning momentum SGD optimizer

Training data extraction on GPT-2

ilpyt: imitation learning library with modular, baseline implementations in Pytorch