paper-with-me

Papers

Universal Conceptual Structure in Neural Translation: Probing NLLB-200's Multilingual Geometry

2026-02-27 · Kyle Elliott Mathewson arxiv

Do neural machine translation models learn language-universal conceptual representations, or do they merely cluster languages by surface similarity? We investigate this question by probing the representation geometry of Meta's NLLB-200, a 200-language encoder-decoder Transformer, through six experiments that bridge NLP interpretability with cognitive science theories of multilingual lexical organization. Using the Swadesh core vocabulary list embedded across 135 languages, we find that the model's embedding distances significantly correlate with phylogenetic distances from the Automated Similarity Judgment Program ($ρ= 0.13$, $p = 0.020$), demonstrating that NLLB-200 has implicitly learned the genealogical structure of human languages. We show that frequently colexified concept pairs from the CLICS database exhibit significantly higher embedding similarity than non-colexified pairs ($U = 42656$, $p = 1.33 \times 10^{-11}$, $d = 0.96$), indicating that the model has internalized universal conceptual associations. Per-language mean-centering of embeddings improves the between-concept to within-concept distance ratio by a factor of 1.19, providing geometric evidence for a language-neutral conceptual store analogous to the anterior temporal lobe hub identified in bilingual neuroimaging. Semantic offset vectors between fundamental concept pairs (e.g., man to woman, big to small) show high cross-lingual consistency (mean cosine = 0.84), suggesting that second-order relational structure is preserved across typologically diverse languages. We release InterpretCognates, an open-source interactive toolkit for exploring these phenomena, alongside a fully reproducible analysis pipeline.

📄 PDF Abstract BibTeX arXiv:2603.02258

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Translation

Similar Papers 제목 키워드 기반

AfriNLLB: Efficient Translation Models for African Languages

2026-02-10 · Yasmin Moslem, Aman Kassahun Wassie, Amanuel Gizachew Abebe arxiv

In this work, we present AfriNLLB, a series of lightweight models for efficient translation from and into African languages. AfriNLLB supports 15 language pairs (30 translation directions), including Swahili, Hausa, Yoru…

Knowledge Distillation

Semantic Prosody in Machine Translation: the English-Chinese Case of Passive Structures

2025-10-16 · Xinyue Ma, Pol Pastells, Mireia Farrús, Mariona Taulé arxiv

Semantic prosody is a collocational meaning formed through the co-occurrence of a linguistic unit and a consistent series of collocates, which should be treated separately from semantic meaning. Since words that are lite…

Machine Translation

Improving Low-Resource Machine Translation via Round-Trip Reinforcement Learning

2026-01-18 · Ahmed Attia, Alham Fikri Aji arxiv

Low-resource machine translation (MT) has gained increasing attention as parallel data from low-resource language communities is collected, but many approaches for improving low-resource MT remain underexplored. We inves…

Reinforcement LearningMachine Translation

Fine-tuning Large Language Models for Adaptive Machine Translation

2023-12-20 · Yasmin Moslem, Rejwanul Haque, Andy Way

This paper presents the outcomes of fine-tuning Mistral 7B, a general-purpose large language model (LLM), for adaptive machine translation (MT). The fine-tuning process involves utilising a combination of zero-shot and o…

In-Context LearningLanguage ModellingLarge Language ModelMachine Translation+1

Domain-Specific Translation with Open-Source Large Language Models: Resource-Oriented Analysis

2024-12-08 · Aman Kassahun Wassie, Mahdi Molaei, Yasmin Moslem

In this work, we compare the domain-specific translation performance of open-source autoregressive decoder-only large language models (LLMs) with task-oriented machine translation (MT) models. Our experiments focus on th…

DecoderKnowledge DistillationMachine TranslationTranslation