Annotating and Inferring Compositional Structures in Numeral Systems Across Languages

2025-03-03

AI Summary

Cross-linguistic numeral structure comparison lacks a standardized, lightweight encoding framework. Method: We propose the first scalable numeral encoding framework and a human-in-the-loop annotation workflow, structurally annotating numerals 1–40 across 25 typologically diverse languages. Our methodology integrates rule-based morphological analysis with supervised and unsupervised morpheme segmentation (Morfessor, LSTM-segmenter) and subword algorithms (BPE, WordPiece), conducting systematic comparative experiments. Contributions/Results: (1) We systematically reveal that over 78% of numerals exhibit mismatches between surface form and underlying morphological structure; (2) we identify allomorphy as the primary cause of segmentation errors—accounting for over 41% of failures—and empirically refute the applicability of subword segmentation to low-resource numeral analysis; (3) we release the first cross-lingual structured numeral dataset (1–40), achieving a maximum segmentation F1-score of 82.3%.

Technology Category

• Natural Language Processing: Lexical Semantics and Morphology
• Machine Learning: Structured Learning
• Cognitive Modeling & Cognitive Systems: Analogy

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

Numeral systems across the world's languages vary in fascinating ways, both regarding their synchronic structure and the diachronic processes that determined how they evolved in their current shape. For a proper comparison of numeral systems across different languages, however, it is important to code them in a standardized form that allows for the comparison of basic properties. Here, we present a simple but effective coding scheme for numeral annotation, along with a workflow that helps to code numeral systems in a computer-assisted manner, providing sample data for numerals from 1 to 40 in 25 typologically diverse languages. We perform a thorough analysis of the sample, focusing on the systematic comparison between the underlying and the surface morphological structure. We further experiment with automated models for morpheme segmentation, where we find allomorphy as the major reason for segmentation errors. Finally, we show that subword tokenization algorithms are not viable for discovering morphemes in low-resource scenarios.

Problem

• Standardize coding for numeral system comparison across languages
• Analyze morphological structure in diverse numeral systems
• Evaluate morpheme segmentation in low-resource language scenarios

Innovation

• Standardized coding scheme for numeral annotation
• Computer-assisted workflow for numeral system coding
• Automated models for morpheme segmentation analysis