Papers › An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from...

An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces

26 Sep 2021Findings (EMNLP) 2021 11arXiv:2109.12640archive 2025-07-28

Kelly Marchisio, Youngser Park, Ali Saad-Eldin, Anton Alyakin, Kevin Duh, Carey Priebe, Philipp Koehn

Much recent work in bilingual lexicon induction (BLI) views word embeddings as vectors in Euclidean space. As such, BLI is typically solved by finding a linear transformation that maps embeddings to a common space. Alternatively, word embeddings may be understood as nodes in a weighted graph. This framing allows us to examine a node's graph neighborhood without assuming a linear transform, and exploits new techniques from the graph matching optimization literature. These contrasting approaches have not been compared in BLI so far. In this work, we study the behavior of Euclidean versus graph-based approaches to BLI under differing data conditions and show that they complement each other when combined. We release our code at https://github.com/kellymarchisio/euc-v-graph-bli.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

kellymarchisio/euc-v-graph-bli officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Bilingual Lexicon InductionGraph MatchingWord Embeddings

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections