# A Crosslingual Investigation of Conceptualization in 1335 Languages

arXiv: https://arxiv.org/abs/2305.08475 · HTML: https://mlsanity.com/paper/2305.08475/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 68 references that are in the map.
- First posted on arXiv 15 May 2023.

## Builds on (most cited first, 12 of 12)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [How multilingual is Multilingual BERT?](https://mlsanity.com/paper/1906.01502/) (2019)
- [Are All Languages Created Equal in Multilingual BERT?](https://mlsanity.com/paper/2005.09093/) (2020)
- [Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing](https://mlsanity.com/paper/1807.00914/) (2018)
- [End-to-End Neural Word Alignment Outperforms GIZA++](https://mlsanity.com/paper/2004.14675/) (2020)
- [Semantic Structure and Interpretability of Word Embeddings](https://mlsanity.com/paper/1711.00331/) (2017)
- [Past, Present, Future: A Computational Investigation of the Typology of Tense in 1000 Languages](https://mlsanity.com/paper/1704.08914/) (2017)
- [Language Embeddings Sometimes Contain Typological Generalizations](https://mlsanity.com/paper/2301.08115/) (2023)
- [Towards a Broad Coverage Named Entity Resource: A Data-Efficient Approach for Many Diverse Languages](https://mlsanity.com/paper/2201.12219/) (2022)
- [MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning](https://mlsanity.com/paper/2102.04009/) (2021)
- [CaMEL: Case Marker Extraction without Labels](https://mlsanity.com/paper/2203.10010/) (2022)
- [Neural Baselines for Word Alignment](https://mlsanity.com/paper/2009.13116/) (2020)

## Built on by (most cited first, 11 of 11)

- [OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining](https://mlsanity.com/paper/2311.08849/) (2023)
- [Crosslingual Transfer Learning for Low-Resource Languages Based on Multilingual Colexification Graphs](https://mlsanity.com/paper/2305.12818/) (2023)
- [Is Prompt-Based Finetuning Always Better than Vanilla Finetuning? Insights from Cross-Lingual Language Understanding](https://mlsanity.com/paper/2307.07880/) (2023)
- [GradSim: Gradient-Based Language Grouping for Effective Multilingual Training](https://mlsanity.com/paper/2310.15269/) (2023)
- [A study of conceptual language similarity: comparison and evaluation](https://mlsanity.com/paper/2305.13401/) (2023)
- [X-PARADE: Cross-Lingual Textual Entailment and Information Divergence across Paragraphs](https://mlsanity.com/paper/2309.08873/) (2023)
- [On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions](https://mlsanity.com/paper/2406.10885/) (2024)
- [LangSAMP: Language-Script Aware Multilingual Pretraining](https://mlsanity.com/paper/2409.18199/) (2024)
- [Patterns of Persistence and Diffusibility across the World's Languages](https://mlsanity.com/paper/2401.01698/) (2024)
- [Assessing the Role of Lexical Semantics in Cross-lingual Transfer through Controlled Manipulations](https://mlsanity.com/paper/2408.07599/) (2024)
- [A Top-down Graph-based Tool for Modeling Classical Semantic Maps: A Crosslinguistic Case Study of Supplementary Adverbs](https://mlsanity.com/paper/2412.01423/) (2024)

## Abstract (arXiv)

Languages differ in how they divide up the world into concepts and words; e.g., in contrast to English, Swahili has a single concept for `belly' and `womb'. We investigate these differences in conceptualization across 1,335 languages by aligning concepts in a parallel corpus. To this end, we propose Conceptualizer, a method that creates a bipartite directed alignment graph between source language concepts and sets of target language strings. In a detailed linguistic analysis across all languages for one concept (`bird') and an evaluation on gold standard data for 32 Swadesh concepts, we show that Conceptualizer has good alignment accuracy. We demonstrate the potential of research on conceptualization in NLP with two experiments. (1) We define crosslingual stability of a concept as the degree to which it has 1-1 correspondences across languages, and show that concreteness predicts stability. (2) We represent each language by its conceptualization pattern for 83 concepts, and define a similarity measure on these representations. The resulting measure for the conceptual similarity of two languages is complementary to standard genealogical, typological, and surface similarity measures. For four out of six language families, we can assign languages to their correct family based on conceptual similarity with accuracy between 54% and 87%.