mlsanityData to 7 Oct 2026

Continuous multilinguality with language vectors

arXiv 1612.07486 ↗First posted 22 Dec 2016cs.CLcited by 20

Not on the map. Why?

Abstract (arXiv)

Most existing models for multilingual natural language processing (NLP) treat language as a discrete category, and make predictions for either one language or the other. In contrast, we propose using continuous vector representations of language. We show that these can be learned efficiently with a character-based neural language model, and used to improve inference about language varieties not seen during training. In experiments with 1303 Bible translations into 990 different languages, we empirically explore the capacity of multilingual language models, and also show that the language vectors capture genetic relationships between languages.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 2; 2023: 2; 2024: 5; 2025: 3; 2026: 1.

20 papers.

Sort:

By area:

  1. 2021Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inferencecited by 96
  2. 2025A Survey of Multilingual Reasoning in Language Modelscited by 31
  3. 2024Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book?cited by 23
  4. 2021Does Typological Blinding Impede Cross-Lingual Sharing?cited by 9
  5. 2023Language Embeddings Sometimes Contain Typological Generalizationscited by 9
  6. 2024Multilingual Gradient Word-Order Typology from Universal Dependenciescited by 9
  7. 2021Language Embeddings for Typology and Cross-lingual Transfer Learningcited by 8
  8. 2024Large Language Models are Easily Confused: A Quantitative Metric, Security Implications and Typological Analysiscited by 7
  9. 2022Measuring Geographic Performance Disparities of Offensive Language Classifierscited by 5
  10. 2021Discovering Representation Sprachbund For Multilingual Pre-Trainingcited by 4
  11. 2021On the Universality of Deep Contextual Language Modelscited by 4
  12. 2025Language Models Are Implicitly Continuouscited by 4
8 more
  1. 2021Towards Zero-shot Language Modelingcited by 3
  2. 2025Neighbors and relatives: How do speech embeddings reflect linguistic connections across the world?cited by 3
  3. 2024LangSAMP: Language-Script Aware Multilingual Pretrainingcited by 2
  4. 2022Informative Language Representation Learning for Massively Multilingual Neural Machine Translationcited by 1
  5. 2021We went to look for meaning and all we got were these lousy representations: aspects of meaning representation for computational semanticscited by 0
  6. 2023mPLM-Sim: Better Cross-Lingual Similarity and Transfer in Multilingual Pretrained Language Modelscited by 0
  7. 2024MaiNLP at SemEval-2024 Task 1: Analyzing Source Language Selection in Cross-Lingual Textual Relatednesscited by 0
  8. 2026Self-Supervised Lexical Representation Learning for Fast, Large-Scale Phylogenetic Inferencecited by 0