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

TCNN Temporal convolutional neural network for real-time speech enhancement in the time domain

This is a repository for a semantic segmentation inference API using the OpenVINO toolkit

This is our ARTS test set, an enriched test set to probe Aspect Robustness of ABSA.

Parasite: a tool allowing you to compress and decompress files, to reduce their size

A Python library that provides a simplified alternative to DBAPI 2

Implementation of algorithms for continuous control (DDPG and NAF).

Cache Requests in Deta Bases and Echo them with Deta Micros

An alarm clock coded in Python 3 with Tkinter

Official implementation of CVPR2020 paper "Deep Generative Model for Robust Imbalance Classification"

SimpleDepthEstimation - An unified codebase for NN-based monocular depth estimation methods

PyTorch Implementation for AAAI'21 "Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response Selection"

An end-to-end implementation of intent prediction with Metaflow and other cool tools

Testing the Facial Emotion Recognition (FER) algorithm on animations

Alphabetical Letter Recognition

HINet: Half Instance Normalization Network for Image Restoration

Self-Supervised Learning of Event-based Optical Flow with Spiking Neural Networks

Repo for "Physion: Evaluating Physical Prediction from Vision in Humans and Machines" submission to NeurIPS 2021 (Datasets & Benchmarks track)

Referring Video Object Segmentation

This program presents convolutional kernel density estimation, a method used to detect intercritical epilpetic spikes (IEDs)

'Aligned mixture of latent dynamical systems' (amLDS) for stimulus decoding probabilistic manifold alignment across animals. P. Herrero-Vidal et al. NeurIPS 2021 code.