An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 26 of its 48 references that are in the map. First posted on arXiv 26 Sep 2021.
Builds on
26 of 48 references.
References · 26
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
- 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
- 2016Enriching Word Vectors with Subword Informationcited by 1,578
- 2017Word Translation Without Parallel Datacited by 480
- 2018A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddingscited by 145
- 2018Gromov-Wasserstein Alignment of Word Embedding Spacescited by 119
- 2018Unsupervised Alignment of Embeddings with Wasserstein Procrustescited by 96
- 2018Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterioncited by 69
- 2018On the Limitations of Unsupervised Bilingual Dictionary Inductioncited by 61
- 2019How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptionscited by 48
- 2020When Does Unsupervised Machine Translation Work?cited by 38
- 2019An Effective Approach to Unsupervised Machine Translationcited by 37
14 more
- 2019Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spacescited by 35
- 2019Do We Really Need Fully Unsupervised Cross-Lingual Embeddings?cited by 31
- 2020LNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent Spacecited by 23
- 2018Learning Multilingual Word Embeddings in Latent Metric Space: A Geometric Approachcited by 22
- 2019Analyzing the Limitations of Cross-lingual Word Embedding Mappingscited by 18
- 2019GraSPy: Graph Statistics in Pythoncited by 15
- 2019Are Girls Neko or Sh=ojo? Cross-Lingual Alignment of Non-Isomorphic Embeddings with Iterative Normalizationcited by 15
- 2018Improving Cross-Lingual Word Embeddings by Meeting in the Middlecited by 13
- 2019Interactive Refinement of Cross-Lingual Word Embeddingscited by 13
- 2018A Discriminative Latent-Variable Model for Bilingual Lexicon Inductioncited by 8
- 2018Characterizing Departures from Linearity in Word Translationcited by 7
- 2020Why Overfitting Isn't Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionariescited by 7
- 2019A Resource-Free Evaluation Metric for Cross-Lingual Word Embeddings Based on Graph Modularitycited by 5
- 2017Low-resource bilingual lexicon extraction using graph based word embeddingscited by 1
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 1.
2 papers.