# Emerging Language Spaces Learned From Massively Multilingual Corpora

arXiv: https://arxiv.org/abs/1802.00273 · HTML: https://mlsanity.com/paper/1802.00273/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Feb 2018.

## Built on by (most cited first, 9 of 9)

- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference](https://mlsanity.com/paper/2110.03742/) (2021)
- [Language Embeddings Sometimes Contain Typological Generalizations](https://mlsanity.com/paper/2301.08115/) (2023)
- [Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction](https://mlsanity.com/paper/2306.06804/) (2023)
- [Can Machine Translation Bridge Multilingual Pretraining and Cross-lingual Transfer Learning?](https://mlsanity.com/paper/2403.16777/) (2024)
- [Discovering Representation Sprachbund For Multilingual Pre-Training](https://mlsanity.com/paper/2109.00271/) (2021)
- [ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpus](https://mlsanity.com/paper/2107.06632/) (2021)
- [Grounded and Well-rounded: A Methodological Approach to the Study of Cross-modal and Cross-lingual Grounding](https://mlsanity.com/paper/2310.11938/) (2023)
- [Direct Neural Machine Translation with Task-level Mixture of Experts models](https://mlsanity.com/paper/2310.12236/) (2023)

## Abstract (arXiv)

Translations capture important information about languages that can be used as implicit supervision in learning linguistic properties and semantic representations. In an information-centric view, translated texts may be considered as semantic mirrors of the original text and the significant variations that we can observe across various languages can be used to disambiguate a given expression using the linguistic signal that is grounded in translation. Parallel corpora consisting of massive amounts of human translations with a large linguistic variation can be applied to increase abstractions and we propose the use of highly multilingual machine translation models to find language-independent meaning representations. Our initial experiments show that neural machine translation models can indeed learn in such a setup and we can show that the learning algorithm picks up information about the relation between languages in order to optimize transfer leaning with shared parameters. The model creates a continuous language space that represents relationships in terms of geometric distances, which we can visualize to illustrate how languages cluster according to language families and groups. Does this open the door for new ideas of data-driven language typology with promising models and techniques in empirical cross-linguistic research?