Meemi: A Simple Method for Post-processing and Integrating Cross-lingual Word Embeddings

TL;DR

Meemi introduces a non-orthogonal post-processing step for cross-lingual word embeddings that enhances the alignment and quality of multilingual spaces, leading to improved performance in various NLP tasks.

Contribution

The paper proposes a novel non-orthogonal transformation method for post-processing cross-lingual embeddings, improving multilingual integration and monolingual space quality.

Findings

Enhanced cross-lingual embedding alignment

Improved performance on dictionary induction and word similarity tasks

Better results in cross-lingual NLP applications

Abstract

Word embeddings have become a standard resource in the toolset of any Natural Language Processing practitioner. While monolingual word embeddings encode information about words in the context of a particular language, cross-lingual embeddings define a multilingual space where word embeddings from two or more languages are integrated together. Current state-of-the-art approaches learn these embeddings by aligning two disjoint monolingual vector spaces through an orthogonal transformation which preserves the structure of the monolingual counterparts. In this work, we propose to apply an additional transformation after this initial alignment step, which aims to bring the vector representations of a given word and its translations closer to their average. Since this additional transformation is non-orthogonal, it also affects the structure of the monolingual spaces. We show that our approach both improves the integration of the monolingual spaces as well as the quality of the monolingual spaces themselves. Furthermore, because our transformation can be applied to an arbitrary number of languages, we are able to effectively obtain a truly multilingual space. The resulting (monolingual and multilingual) spaces show consistent gains over the current state-of-the-art in standard intrinsic tasks, namely dictionary induction and word similarity, as well as in extrinsic tasks such as cross-lingual hypernym discovery and cross-lingual natural language inference.