Data Augmentation by Backtranslation (DAB) ヽ( •_-)ᕗ

Cross-lingual Language Model (XLM) pretraining and Model-Agnostic Meta-Learning (MAML) for fast adaptation of deep networks

Bangla Text Augmentation

Implementing 5 Different Approaches To Augmenting Data For Natural Language Processing Tasks.

Low resource machine translation using Transformers and Iterative Back translation

Source code and data for paper ``Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing" in ACL 2020.

A PyTorch implementation of a transformer network trained using back-translation

Reproducible Legal NER pipeline using RoBERTa, LegalBERT, linguistic features, and back-translation. Implements data preparation, spaCy training configs, and evaluation on the InLegalNER corpus with 14 fine-grained entity types.

An attempt to make Back-Translation differentiable, using probability weighted embeddings for predicted translations in the nucleus of the predicted distribution over target language sentences.

Cultural Translation Tool

This repo offers a Python script using NLPAug library & RTT to augment text datasets. It processes TXT files in "data/" folder, translating text and creating augmented versions. Augmented data enhances NLP tasks like chatbot training & text classification. Includes overview of techniques, applications & implementation.

Low resource language machine translation(az,be,tr -> en).

Tool to detect translation errors using GPT and back translation.

Common approaches to text augmentation, from random text-editing perturbations, back translation, to model-based transformations.

Code associated with the "Enhanced Cognitive Distortions Detection and Classification through Data Augmentation Techniques" paper

Noise Identification, Noise reduction, and Sentiment Analysis on Bangla Noisy Texts

A text generation library to paraphrase image captions using back translations or transfer learning.

BackTranslation Experiment