A neural word aligner based on multilingual BERT

Code for our paper "Mask-Align: Self-Supervised Neural Word Alignment" in ACL 2021

Improving Word Translation via Two-Stage Contrastive Learning (ACL 2022). Keywords: Bilingual Lexicon Induction, Word Translation, Cross-Lingual Word Embeddings.

A 2024 Reading List for Bilingual Lexicon Induction (BLI) / Word Translation. Frequently Updated.

X-SRL Dataset. Including the code for the SRL annotation projection tool and an out-of-the-box word alignment tool based on Multilingual BERT embeddings.

Improving Bilingual Lexicon Induction with Cross-Encoder Reranking (Findings of EMNLP 2022). Keywords: Bilingual Lexicon Induction, Word Translation, Cross-Lingual Word Embeddings.

This is the implementation of word aligner using Hidden Markov Model

This project provide an API to perform word alignment

Are Girls Neko or Shōjo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalization (ACL 2019)

Enhanced awesome-align for low-resource languages and noise simulation: https://arxiv.org/abs/2301.09685

Why Overfitting Isn't Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries (ACL 2020)

Create "pretty" graphs for aligned sentences

WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span Prediction, to appear at ACL 2023 main conference.

A pipeline for POS tagging, sentence alignment, word alignment, and transliteration of texts in 30+ languages.

Using alignments and posteriorgrams extracted from lyrics as novel input into source separation models

Java application for creating bilingual word alignments

Inference library and evaluation script for WSPAlign (https://github.com/qiyuw/WSPAlign)

A pipeline for machine translation (using OPUS-MT models) of parliamentary text collections in 30+ languages (ParlaMint corpora). The pipeline includes parsing TEI XLM and CONLL-u files, linguistic processing with the Stanza pipeline, machine translation and word alignment with the Eflomal tool.

Demonstration of AI/neural word alignment of English & Japanese text using mBERT-based machine learning models.

Assignment 1: Word Alignment in 'Statistical Machine Translation' course by Dr. Roee Aharoni at Bar-Ilan University.