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

Official PyTorch Implementation of Rank & Sort Loss [ICCV2021]

PyTorch ,ONNX and TensorRT implementation of YOLOv4

Code for "Offline Meta-Reinforcement Learning with Advantage Weighting" [ICML 2021]

Huawei Hackathon 2021 - Sweden (Stockholm)

Perform zero-order Hankel Transform for an 1D array (float or real valued).

An Efficient Training Approach for Very Large Scale Face Recognition or F²C for simplicity.

A benchmark for the task of translation suggestion

Face-Recognition-Attendence-System - This face recognition Attendence system using Python

A Comparative Review of Recent Kinect-Based Action Recognition Algorithms (TIP2020, Matlab codes)

Compute FID scores with PyTorch.

Official code for the paper: Deep Graph Matching under Quadratic Constraint (CVPR 2021)

The official PyTorch implementation of Curriculum by Smoothing (NeurIPS 2020, Spotlight).

Official code of the paper "Expanding Low-Density Latent Regions for Open-Set Object Detection" (CVPR 2022)

Modelisation on galaxy evolution using PEGASE-HR

Streamlit tool to explore coco datasets

Robotic Process Automation in Windows and Linux by using Driagrams.net BPMN diagrams.

Repo for the paper "DiLBERT: Cheap Embeddings for Disease Related Medical NLP"

CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator

Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation

Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks