SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.01207 · 2021

Similarity of Sentence Representations in Multilingual LMs: Resolving Conflicting Literature and Case Study of Baltic Languages

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Low-resource languages, such as Baltic languages, benefit from Large Multilingual Models (LMs) that possess remarkable cross-lingual transfer performance capabilities. This work is an interpretation and analysis study into cross-lingual representations of Multilingual LMs. Previous works hypothesized that these LMs internally project representations of different languages into a shared cross-lingual space. However, the literature produced contradictory results. In this paper, we revisit the prior work claiming that "BERT is not an Interlingua" and show that different languages do converge to a shared space in such language models with another choice of pooling strategy or similarity index. Then, we perform cross-lingual representational analysis for the two most popular multilingual LMs employing 378 pairwise language comparisons. We discover that while most languages share joint cross-lingual space, some do not. However, we observe that Baltic languages do belong to that shared space. The code is available at https://github.com/TartuNLP/xsim.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2109.01207")
get_code_for_paper("2109.01207")
have("2109.01207")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2109.01207.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2109.01207.svg)](https://syntology.ai/paper/2109.01207)

Connect an agent — have() is free.