Translation from the Information Bottleneck Perspective: an Efficiency Analysis of Spatial Prepositions in Bitexts

2026-03-20

AI Summary

This study investigates whether information-efficiency pressures shape natural language translation, focusing on how spatial prepositions across languages balance fidelity and conciseness. Framing translation as an Information Bottleneck (IB) optimization problem—with the source sentence as input and the target sentence as a compressed representation—we examine whether real-world preposition translations approach the IB-optimal frontier. Applying the IB framework to authentic bilingual corpora for lexical semantic analysis, we combine a low-rank projection model (D=5), human similarity judgments (N=35), and Spearman correlation evaluation. Results show that actual preposition translations significantly outperform counterfactual alternatives (ρ=0.78), providing preliminary evidence that human translation is driven by constraints of cognitive and communicative efficiency.

Technology Category

• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Knowledge Representation and Reasoning: Preferences
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Efficient communication requires balancing informativity and simplicity when encoding meanings. The Information Bottleneck (IB) framework captures this trade-off formally, predicting that natural language systems cluster near an optimal accuracy-complexity frontier. While supported in visual domains such as colour and motion, linguistic stimuli such as words in sentential context remain unexplored. We address this gap by framing translation as an IB optimisation problem, treating source sentences as stimuli and target sentences as compressed meanings. This allows IB analyses to be performed directly on bitexts rather than controlled naming experiments. We applied this to spatial prepositions across English, German and Serbian translations of a French novel. To estimate informativity, we conducted a pile-sorting pilot-study (N=35) and obtained similarity judgements of pairs of prepositions. We trained a low-rank projection model (D=5) that predicts these judgements (Spearman correlation: 0.78). Attested translations of prepositions lie closer to the IB optimal frontier than counterfactual alternatives, offering preliminary evidence that human translators exhibit communicative efficiency pressure in the spatial domain. More broadly, this work suggests that translation can serve as a window into the cognitive efficiency pressures shaping cross-linguistic semantic systems.

Problem

• Information Bottleneck
• translation
• spatial prepositions
• communicative efficiency
• bitexts

Innovation

• Information Bottleneck
• translation efficiency
• spatial prepositions
• bitext analysis
• communicative efficiency