# Investigating Multilingual NMT Representations at Scale

arXiv: https://arxiv.org/abs/1909.02197 · HTML: https://mlsanity.com/paper/1909.02197/

## Key facts

- Cited by 68 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2019.

## Built on by (most cited first, 30 of 68)

- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning](https://mlsanity.com/paper/2111.10952/) (2021)
- [Similarity of Neural Network Models: A Survey of Functional and Representational Measures](https://mlsanity.com/paper/2305.06329/) (2023)
- [Neural Machine Translation for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2106.15115/) (2021)
- [mSLAM: Massively multilingual joint pre-training for speech and text](https://mlsanity.com/paper/2202.01374/) (2022)
- [Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference](https://mlsanity.com/paper/2110.03742/) (2021)
- [The Geometry of Multilingual Language Model Representations](https://mlsanity.com/paper/2205.10964/) (2022)
- [MURAL: Multimodal, Multitask Retrieval Across Languages](https://mlsanity.com/paper/2109.05125/) (2021)
- [IndicBART: A Pre-trained Model for Indic Natural Language Generation](https://mlsanity.com/paper/2109.02903/) (2021)
- [Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity](https://mlsanity.com/paper/2406.14479/) (2024)
- [Language Tags Matter for Zero-Shot Neural Machine Translation](https://mlsanity.com/paper/2106.07930/) (2021)
- [Examining Scaling and Transfer of Language Model Architectures for Machine Translation](https://mlsanity.com/paper/2202.00528/) (2022)
- [Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation?](https://mlsanity.com/paper/2203.08850/) (2022)
- [Towards the Next 1000 Languages in Multilingual Machine Translation: Exploring the Synergy Between Supervised and Self-Supervised Learning](https://mlsanity.com/paper/2201.03110/) (2022)
- [Neuron Specialization: Leveraging intrinsic task modularity for multilingual machine translation](https://mlsanity.com/paper/2404.11201/) (2024)
- [Language Models are Good Translators](https://mlsanity.com/paper/2106.13627/) (2021)
- [Consistency is the key to further mitigating catastrophic forgetting in continual learning](https://mlsanity.com/paper/2207.04998/) (2022)
- [Viewing Knowledge Transfer in Multilingual Machine Translation Through a Representational Lens](https://mlsanity.com/paper/2305.11550/) (2023)
- [Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variables](https://mlsanity.com/paper/2109.04705/) (2021)
- [Does Transliteration Help Multilingual Language Modeling?](https://mlsanity.com/paper/2201.12501/) (2022)
- [How Reliable are Model Diagnostics?](https://mlsanity.com/paper/2105.05641/) (2021)
- [Learning Language-Specific Layers for Multilingual Machine Translation](https://mlsanity.com/paper/2305.02665/) (2023)
- [Unveiling Multilinguality in Transformer Models: Exploring Language Specificity in Feed-Forward Networks](https://mlsanity.com/paper/2310.15552/) (2023)
- [How do Variational Autoencoders Learn? Insights from Representational Similarity](https://mlsanity.com/paper/2205.08399/) (2022)
- [CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translation](https://mlsanity.com/paper/2204.00665/) (2022)
- [Language Embeddings Sometimes Contain Typological Generalizations](https://mlsanity.com/paper/2301.08115/) (2023)
- [How do Multimodal Foundation Models Encode Text and Speech? An Analysis of Cross-Lingual and Cross-Modal Representations](https://mlsanity.com/paper/2411.17666/) (2024)
- [Breaking Down Multilingual Machine Translation](https://mlsanity.com/paper/2110.08130/) (2021)
- [Are Pretrained Multilingual Models Equally Fair Across Languages?](https://mlsanity.com/paper/2210.05457/) (2022)
- [Cross-lingual Similarity of Multilingual Representations Revisited](https://mlsanity.com/paper/2212.01924/) (2022)

## Abstract (arXiv)

Multilingual Neural Machine Translation (NMT) models have yielded large empirical success in transfer learning settings. However, these black-box representations are poorly understood, and their mode of transfer remains elusive. In this work, we attempt to understand massively multilingual NMT representations (with 103 languages) using Singular Value Canonical Correlation Analysis (SVCCA), a representation similarity framework that allows us to compare representations across different languages, layers and models. Our analysis validates several empirical results and long-standing intuitions, and unveils new observations regarding how representations evolve in a multilingual translation model. We draw three major conclusions from our analysis, with implications on cross-lingual transfer learning: (i) Encoder representations of different languages cluster based on linguistic similarity, (ii) Representations of a source language learned by the encoder are dependent on the target language, and vice-versa, and (iii) Representations of high resource and/or linguistically similar languages are more robust when fine-tuning on an arbitrary language pair, which is critical to determining how much cross-lingual transfer can be expected in a zero or few-shot setting. We further connect our findings with existing empirical observations in multilingual NMT and transfer learning.