GARI: Graph Attention for Relative Isomorphism of Arabic Word Embeddings
Not on the map. Why?
Abstract (arXiv)
Bilingual Lexical Induction (BLI) is a core challenge in NLP, it relies on the relative isomorphism of individual embedding spaces. Existing attempts aimed at controlling the relative isomorphism of different embedding spaces fail to incorporate the impact of semantically related words in the model training objective. To address this, we propose GARI that combines the distributional training objectives with multiple isomorphism losses guided by the graph attention network. GARI considers the impact of semantical variations of words in order to define the relative isomorphism of the embedding spaces. Experimental evaluation using the Arabic language data set shows that GARI outperforms the existing research by improving the average P@1 by a relative score of up to 40.95% and 76.80% for in-domain and domain mismatch settings respectively. We release the codes for GARI at https://github.com/asif6827/GARI.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 20 of its 27 references that are in the map. First posted on arXiv 19 Oct 2023.
Builds on
20 of 27 references.
References · 20
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2017Graph Attention Networkscited by 8,854
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
- 2017Word Translation Without Parallel Datacited by 480
- 2018Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyondcited by 434
- 2017A Survey Of Cross-lingual Word Embedding Modelscited by 142
- 2018Phrase-Based & Neural Unsupervised Machine Translationcited by 138
- 2018Gromov-Wasserstein Alignment of Word Embedding Spacescited by 119
- 2018Loss in Translation: Learning Bilingual Word Mapping with a Retrieval Criterioncited by 69
- 2019Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsingcited 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
8 more
- 2019Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spacescited by 35
- 2019Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Frameworkcited by 26
- 2018Learning Multilingual Word Embeddings in Latent Metric Space: A Geometric Approachcited by 22
- 2019Context-Aware Cross-Lingual Mappingcited by 17
- 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
- 2019Antonym-Synonym Classification Based on New Sub-space Embeddingscited by 9
- 2022IsoVec: Controlling the Relative Isomorphism of Word Embedding Spacescited by 7
Built on by
Citing papers per year: 2024: 3.
3 papers.