This repository contains the source code for CalBERT - Code-mixed Adaptive Language representations using BERT, published at AAAI-MAKE 2022, Stanford University.
CalBERT can be used to adapt existing Transformer language representations into another similar language by minimising the semantic space between equivalent sentences in those languages, thus allowing the Transformer to learn representations for words across two languages. It relies on a novel pre-training architecture named Siamese Pre-training to learn task-agnostic and language-agnostic representations. For more information, please refer to the paper.
This framework allows you to perform CalBERT's Siamese Pre-training to learn representations for your own data and can be used to obtain dense vector representations for words, sentences or paragraphs. The base models used to train CalBERT consist of BERT-based Transformer models such as BERT, RoBERTa, XLM, XLNet, DistilBERT, and so on. CalBERT achieves state-of-the-art results on the SAIL and IIT-P Product Reviews datasets. CalBERT is also one of the only models able to learn code-mixed language representations without the need for traditional pre-training methods and is currently one of the few models available for Indian code-mixing such as Hinglish.
We recommend Python 3.9 or higher for CalBERT.
Follow PyTorch - Get Started for further details on how to install PyTorch with or without CUDA.
pip install calbertYou can also clone the current version from the repository and then directly install the package.
pip install -e .You can read the docs to learn more about how to train CalBERT for your own use case.
The following example shows you how to use CalBERT to obtain sentence embeddings.
This framework allows you to also train your own CalBERT models on your own code-mixed data so you can learn embeddings for your custom code-mixed languages. There are various options to choose from in order to get the best embeddings for your language.
First, initialise a model with the base Transformer
from calbert import CalBERT
model = CalBERT('bert-base-uncased')Create a CalBERTDataset using your sentences
from calbert import CalBERTDataset
base_language_sentences = [
"I am going to Delhi today via flight",
"This movie is awesome!"
]
target_language_sentences = [
"Main aaj flight lekar Delhi ja raha hoon.",
"Mujhe yeh movie bahut awesome lagi!"
]
dataset = CalBERTDataset(base_language_sentences, target_language_sentences)Then create a trainer and train the model
from calbert import SiamesePreTrainer
trainer = SiamesePreTrainer(model, dataset)
trainer.train()Our models achieve state-of-the-art results on the SAIL and IIT-P Product Reviews datasets.
More information will be added soon.
This framework can be used for:
- Computing code-mixed as well as plain sentence embeddings
- Obtaining semantic similarities between any two sentences
- Other textual tasks such as clustering, text summarization, semantic search and many more.
If you find this repository useful, please cite our publication CalBERT - Code-mixed Apaptive Language representations using BERT.
@inproceedings{calbert-baral-et-al-2022,
author = {Aditeya Baral and
Aronya Baksy and
Ansh Sarkar and
Deeksha D and
Ashwini M. Joshi},
editor = {Andreas Martin and
Knut Hinkelmann and
Hans{-}Georg Fill and
Aurona Gerber and
Doug Lenat and
Reinhard Stolle and
Frank van Harmelen},
title = {CalBERT - Code-Mixed Adaptive Language Representations Using {BERT}},
booktitle = {Proceedings of the {AAAI} 2022 Spring Symposium on Machine Learning
and Knowledge Engineering for Hybrid Intelligence {(AAAI-MAKE} 2022),
Stanford University, Palo Alto, California, USA, March 21-23, 2022},
series = {{CEUR} Workshop Proceedings},
volume = {3121},
publisher = {CEUR-WS.org},
year = {2022},
url = {http://ceur-ws.org/Vol-3121/short3.pdf},
timestamp = {Fri, 22 Apr 2022 14:55:37 +0200}
}Please feel free to contact us by emailing us to report any issues or suggestions, or if you have any further questions.
Contact: - Aditeya Baral, aditeya.baral@gmail.com
You can also contact the other maintainers listed below.