PragExTra: A Multilingual Corpus of Pragmatic Explicitation in Translation

2025-11-04

AI Summary

This study addresses the lack of computational modeling for pragmatic explicitation—the addition of background information by translators to render implicit cultural meanings explicit. We introduce the first multilingual pragmatic explicitation corpus covering eight language pairs and propose an automatic detection framework based on null alignment and active learning. Methodologically, candidate explicitation instances are identified via null-aligned segments; active learning is employed to maximize annotation efficiency, and cross-lingual modeling leverages TED-Multi and Europarl. Experiments demonstrate that our framework achieves up to 0.88 accuracy and 0.82 F1 across languages—outperforming baselines by 7–8 percentage points. Analysis reveals entity-level and system-level explicitation as the most prevalent types. To our knowledge, this work is the first to formalize pragmatic explicitation as a computationally tractable, quantifiable, and transferable NLP task, establishing both a novel paradigm and foundational resources for cross-lingual pragmatic research.

Technology Category

• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Machine Learning: Active Learning
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Translators often enrich texts with background details that make implicit cultural meanings explicit for new audiences. This phenomenon, known as pragmatic explicitation, has been widely discussed in translation theory but rarely modeled computationally. We introduce PragExTra, the first multilingual corpus and detection framework for pragmatic explicitation. The corpus covers eight language pairs from TED-Multi and Europarl and includes additions such as entity descriptions, measurement conversions, and translator remarks. We identify candidate explicitation cases through null alignments and refined using active learning with human annotation. Our results show that entity and system-level explicitations are most frequent, and that active learning improves classifier accuracy by 7-8 percentage points, achieving up to 0.88 accuracy and 0.82 F1 across languages. PragExTra establishes pragmatic explicitation as a measurable, cross-linguistic phenomenon and takes a step towards building culturally aware machine translation. Keywords: translation, multilingualism, explicitation

Problem

• Modeling pragmatic explicitation computationally in translation
• Building multilingual corpus for detecting cultural adaptation patterns
• Improving machine translation cultural awareness through explicitation analysis

Innovation

• Multilingual corpus for pragmatic explicitation detection
• Active learning refines null alignment candidate selection
• Classifier achieves 0.88 accuracy across eight languages