Lune

EMNLP Findings2021

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

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

Abstract

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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal TransportKelly Marchisio, Ali Saad-Eldin, Kevin Duh, Carey E. Priebe et al.EMNLP 2022 · 1 citation

Builds on3

  1. Interactive Refinement of Cross-Lingual Word EmbeddingsMichelle Yuan, Mozhi Zhang, Benjamin Van Durme, Leah Findlater et al.EMNLP 2020 · 32 citations
  2. A Graph-based Coarse-to-fine Method for Unsupervised Bilingual Lexicon InductionShuo Ren, Shujie Liu, Ming Zhou, Shuai MaACL 2020 · 13 citations
  3. LNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent SpaceTasnim Mohiuddin, M. Saiful Bari, Shafiq Rayhan JotyEMNLP 2020 · 13 citations

Related papers

  1. Enhancing Bilingual Lexicon Induction via Bi-directional Translation Pair RetrievingQiuyu Ding, Hailong Cao, Tiejun ZhaoAAAI 2024 · 3 citations
  2. Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon InductionJinpeng Zhang, Baijun Ji, Nini Xiao, Xiangyu Duan et al.ACL Findings 2021 · 18 citations
  3. Revisiting the Context Window for Cross-lingual Word EmbeddingsRyokan Ri, Yoshimasa TsuruokaACL 2020 · 4 citations
  4. A Structure-Aware Generative Adversarial Network for Bilingual Lexicon InductionBocheng Han, Qian Tao, Lusi Li, Zhihao XiongEMNLP Findings 2023 · 2 citations
  5. IsoVec: Controlling the Relative Isomorphism of Word Embedding SpacesKelly Marchisio, Neha Verma, Kevin Duh, Philipp KoehnEMNLP 2022 · 6 citations
Dusk over the sea between two cliffs drawn in fine vertical lines