# A Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignments

arXiv: https://arxiv.org/abs/1608.05426 · HTML: https://mlsanity.com/paper/1608.05426/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Aug 2016.

## Built on by (most cited first, 6 of 6)

- [Crosslingual Transfer Learning for Low-Resource Languages Based on Multilingual Colexification Graphs](https://mlsanity.com/paper/2305.12818/) (2023)
- [Cross-language Sentence Selection via Data Augmentation and Rationale Training](https://mlsanity.com/paper/2106.02293/) (2021)
- [Graph Neural Networks for Multiparallel Word Alignment](https://mlsanity.com/paper/2203.08654/) (2022)
- [Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging](https://mlsanity.com/paper/2210.09840/) (2022)
- [Bilingual Language Modeling, A transfer learning technique for Roman Urdu](https://mlsanity.com/paper/2102.10958/) (2021)
- [Decipherment-Aware Multilingual Learning in Jointly Trained Language Models](https://mlsanity.com/paper/2406.07231/) (2024)

## Abstract (arXiv)

While cross-lingual word embeddings have been studied extensively in recent years, the qualitative differences between the different algorithms remain vague. We observe that whether or not an algorithm uses a particular feature set (sentence IDs) accounts for a significant performance gap among these algorithms. This feature set is also used by traditional alignment algorithms, such as IBM Model-1, which demonstrate similar performance to state-of-the-art embedding algorithms on a variety of benchmarks. Overall, we observe that different algorithmic approaches for utilizing the sentence ID feature space result in similar performance. This paper draws both empirical and theoretical parallels between the embedding and alignment literature, and suggests that adding additional sources of information, which go beyond the traditional signal of bilingual sentence-aligned corpora, may substantially improve cross-lingual word embeddings, and that future baselines should at least take such features into account.