Cross Lingual Linking

Code for the experiments from our workshop paper "A Comparison of Unsupervised Methods for Ad-hoc Cross-Lingual Document Retrieval" https://www.aclweb.org/anthology/2020.clssts-1.6.pdf

mltm.py 

This is an implementation of the Polylingual Topic Model (Mimno et al., 2009)

doc_linking.py

This contains the two embedding-based method for cross-lingual document retrieval: Wasserstein distance (Balikas et al., 2018) and Cr5 (Josifoski et al., 2019)