Repository for the paper titled: "When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual Transfer"
-
Updated
Nov 10, 2021 - Python
#
multilingual-bert
Here are 9 public repositories matching this topic...
Match celebrity users with their respective tweets by making use of Semantic Textual Similarity on over 900+ celebrity users' 2.5 million+ crawled tweets utilizing SBERT, streamlit, tweepy and FastAPI
rest-api pytorch web-scraping tweepy mypy bert twitter-scraping pytorch-gpu pydantic fastapi python39 streamlit sentence-transformers sbert vector-embeddings streamlit-webapp multilingual-bert python310 llm large-language-model
-
Updated
Nov 21, 2023 - Python
Language Model Decomposition: Quantifying the Dependency and Correlation of Language Models
python nlp natural-language-processing deep-learning transformers pytorch pretrained-models language-models bert roberta xlm-roberta multilingual-bert
-
Updated
Dec 22, 2022 - Python
Code and data for the EMNLP 2020 paper: "Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to Rank"
learning-to-rank parallel-data bertology multilingual-bert semantic-divergences corpus-filtering synthetic-supervision cross-lingual-similarity
-
Updated
Feb 10, 2023 - Python
This repository contains a number of experiments with Multi Lingual Transformer models (Multi-Lingual BERT, DistilBERT, XLM-RoBERTa, mT5 and ByT5) focussed on the Dutch language.
nlp text-classification transformers bert mt5 linearsvc tensorflow2 distilbert xlm-roberta transformers-models multilingual-bert byt5
-
Updated
Oct 30, 2023 - Python
Bias analysis in multilingual BERT using SHAP and fairness metrics (EN, DE, HI)
-
Updated
Aug 4, 2025 - Python
App for medieval multilingual metadata — feeds the Segmentation Dataset and trains the Aquilign aligner
segmentation corpus-data nlp-machine-learning medieval streamlit-webapp multilingual-bert medieval-languages
-
Updated
Sep 17, 2025 - Python
Align Parallel Sentence of 104 Languages with the help of mBERT and LaBSE
-
Updated
Mar 7, 2024 - Python
This repository implements a Multilingual BERT (mBERT) model for performing Parts-of-Speech (POS) Tagging on Assamese-English code-mixed texts.
nlp english parts-of-speech nlp-machine-learning pos-tagging pos-tagger english-language code-mixing assamese code-mixed mbert parts-of-speech-tagging multilingual-bert assamese-text
-
Updated
Dec 8, 2024 - Python
Improve this page
Add a description, image, and links to the multilingual-bert topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the multilingual-bert topic, visit your repo's landing page and select "manage topics."