mlsanityData to 7 Oct 2026

Embedding-Enhanced Giza++: Improving Alignment in Low- and High- Resource Scenarios Using Embedding Space Geometry

arXiv 2104.08721 ↗First posted 18 Apr 2021cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

A popular natural language processing task decades ago, word alignment has been dominated until recently by GIZA++, a statistical method based on the 30-year-old IBM models. New methods that outperform GIZA++ primarily rely on large machine translation models, massively multilingual language models, or supervision from GIZA++ alignments itself. We introduce Embedding-Enhanced GIZA++, and outperform GIZA++ without any of the aforementioned factors. Taking advantage of monolingual embedding spaces of source and target language only, we exceed GIZA++'s performance in every tested scenario for three languages pairs. In the lowest-resource setting, we outperform GIZA++ by 8.5, 10.9, and 12 AER for Ro-En, De-En, and En-Fr, respectively. We release our code at https://github.com/kellymarchisio/ee-giza.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 42 references that are in the map. First posted on arXiv 18 Apr 2021.

Builds on

18 of 42 references.

References · 18

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  3. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  4. 2016Enriching Word Vectors with Subword Informationcited by 1,578
  5. 2017Word Translation Without Parallel Datacited by 480
  6. 2021Word Alignment by Fine-tuning Embeddings on Parallel Corporacited by 186
  7. 2020SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddingscited by 155
  8. 2018A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddingscited by 145
  9. 2019Jointly Learning to Align and Translate with Transformer Modelscited by 75
  10. 2019An Effective Approach to Unsupervised Machine Translationcited by 37
  11. 2019Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spacescited by 35
  12. 2020Accurate Word Alignment Induction from Neural Machine Translationcited by 32
6 more
  1. 2019Adding Interpretable Attention to Neural Translation Models Improves Word Alignmentcited by 30
  2. 2020End-to-End Neural Word Alignment Outperforms GIZA++cited by 28
  3. 2020A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERTcited by 27
  4. 2019A Discriminative Neural Model for Cross-Lingual Word Alignmentcited by 14
  5. 2020On a Novel Application of Wasserstein-Procrustes for Unsupervised Cross-Lingual Learningcited by 6
  6. 2019Learning to Relate from Captions and Bounding Boxescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models
  2. 2024Exploring Alignment in Shared Cross-lingual Spaces
  3. 2023Multilingual Sentence Transformer as A Multilingual Word Aligner
  4. 2025Benchmarking Cross-Lingual Semantic Alignment in Multilingual Embeddings
  5. 2022Cross-Align: Modeling Deep Cross-lingual Interactions for Word Alignment
  6. 2024Concept Space Alignment in Multilingual LLMs
  7. 2025TransAlign: Machine Translation Encoders are Strong Word Aligners, Too
  8. 2026Less is More: Adapting Text Embeddings for Low-Resource Languages with Small Scale Noisy Synthetic Data