This repository contains the code, data, and models of the paper titled "CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs" published in Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL’23), July 9-14, 2023.

CogNet: a large-scale, high-quality cognate database for 338 languages, 1.07M words, and 8.1 million cognates

Improving Indonesian text classification using multilingual language model

Implementation of ICLR 2022 paper "Enhancing Cross-lingual Transfer by Manifold Mixup".

Official implementation of "CONCRETE: Improving Cross-lingual Fact Checking with Cross-lingual Retrieval" (COLING'22)

Cross Lingual Language models for making search engines for Holy Quran and Sahih Hadiths

[EMNLP 2022] Discovering Language-neutral Sub-networks in Multilingual Language Models.

Cascading Adaptors to Leverage English Data to Improve Performance ofQuestion Answering for Low-Resource Languages

In this work we applied multilingual zero-shot transfer concept for the task of toxic comments detection. This concept allows a model trained only on a single-language dataset to work in arbitrary language, even low-resource.

Code for importance-weighted domain alignment, and the paper “Cross-Lingual Transfer with Class-Weighted Language-Invariant Representations”.

This repository contains the code for the experiments related to higher-level semantic tasks and related to the meta-learning from: "From Zero to Hero: On the Limitations of Zero Shot Cross-Lingual Transfer"

Author's implementation of the paper https://www.aclweb.org/anthology/2021.ltedi-1.30/

This is a project proposal to implement Yan et al.'s (2020) mBERT-Unaligned for cross-lingual RDs with Japanese, German and Italian untranslatable terms

Improving Quality of Multilingual Question Answering and Cross-Lingual Transfer using Multitask Learning, Knowledge Distillation, and Data Augmentation