BERnaT: Basque Encoders for Representing Natural Textual Diversity

• URL: http://arxiv.org/abs/2512.03903v1
• Date: Wed, 03 Dec 2025 15:50:42 GMT
• Title: BERnaT: Basque Encoders for Representing Natural Textual Diversity
• Authors: Ekhi Azurmendi, Joseba Fernandez de Landa, Jaione Bengoetxea, Maite Heredia, Julen Etxaniz, Mikel Zubillaga, Ander Soraluze, Aitor Soroa,
• Abstract summary: We argue that language models should aim to capture the full spectrum of language variation rather than relying solely on standardized text.<n>We construct new corpora combining standard, social media, and historical sources, and pre-train the BERnaT family of encoder-only models in three configurations.<n>Results show that models trained on both standard and diverse data consistently outperform those trained on standard corpora.
• Score: 7.357065915404815
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language models depend on massive text corpora that are often filtered for quality, a process that can unintentionally exclude non-standard linguistic varieties, reduce model robustness and reinforce representational biases. In this paper, we argue that language models should aim to capture the full spectrum of language variation (dialectal, historical, informal, etc.) rather than relying solely on standardized text. Focusing on Basque, a morphologically rich and low-resource language, we construct new corpora combining standard, social media, and historical sources, and pre-train the BERnaT family of encoder-only models in three configurations: standard, diverse, and combined. We further propose an evaluation framework that separates Natural Language Understanding (NLU) tasks into standard and diverse subsets to assess linguistic generalization. Results show that models trained on both standard and diverse data consistently outperform those trained on standard corpora, improving performance across all task types without compromising standard benchmark accuracy. These findings highlight the importance of linguistic diversity in building inclusive, generalizable language models.

Related papers

• NoveltyBench: Evaluating Language Models for Humanlike Diversity [21.6078675947446]
  NoveltyBench is a benchmark designed to evaluate the ability of language models to produce multiple distinct and high-quality outputs.<n>We evaluate 20 leading language models and find that current state-of-the-art systems generate significantly less diversity than human writers.
  arXiv  Detail & Related papers  (2025-04-07T16:14:23Z)
• Multilingual Conceptual Coverage in Text-to-Image Models [98.80343331645626]
  "Conceptual Coverage Across Languages" (CoCo-CroLa) is a technique for benchmarking the degree to which any generative text-to-image system provides multilingual parity to its training language in terms of tangible nouns. For each model we can assess "conceptual coverage" of a given target language relative to a source language by comparing the population of images generated for a series of tangible nouns in the source language to the population of images generated for each noun under translation in the target language.
  arXiv  Detail & Related papers  (2023-06-02T17:59:09Z)
• Universal and Independent: Multilingual Probing Framework for Exhaustive Model Interpretation and Evaluation [0.04199844472131922]
  We present and apply the GUI-assisted framework allowing us to easily probe a massive number of languages. Most of the regularities revealed in the mBERT model are typical for the western-European languages. Our framework can be integrated with the existing probing toolboxes, model cards, and leaderboards.
  arXiv  Detail & Related papers  (2022-10-24T13:41:17Z)
• CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark [144.05723617401674]
  General-purpose language intelligence evaluation has been a longstanding goal for natural language processing. We argue that for general-purpose language intelligence evaluation, the benchmark itself needs to be comprehensive and systematic. We propose CUGE, a Chinese Language Understanding and Generation Evaluation benchmark with the following features.
  arXiv  Detail & Related papers  (2021-12-27T11:08:58Z)
• Analyzing the Limits of Self-Supervision in Handling Bias in Language [52.26068057260399]
  We evaluate how well language models capture the semantics of four tasks for bias: diagnosis, identification, extraction and rephrasing. Our analyses indicate that language models are capable of performing these tasks to widely varying degrees across different bias dimensions, such as gender and political affiliation.
  arXiv  Detail & Related papers  (2021-12-16T05:36:08Z)
• Cross-Lingual Fine-Grained Entity Typing [26.973783464706447]
  We present a unified cross-lingual fine-grained entity typing model capable of handling over 100 languages. We analyze this model's ability to generalize to languages and entities unseen during training.
  arXiv  Detail & Related papers  (2021-10-15T03:22:30Z)
• Discovering Representation Sprachbund For Multilingual Pre-Training [139.05668687865688]
  We generate language representation from multilingual pre-trained models and conduct linguistic analysis. We cluster all the target languages into multiple groups and name each group as a representation sprachbund. Experiments are conducted on cross-lingual benchmarks and significant improvements are achieved compared to strong baselines.
  arXiv  Detail & Related papers  (2021-09-01T09:32:06Z)
• Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalan [0.05277024349608833]
  This work focuses on Catalan with the aim of exploring what extent a medium-sized monolingual language model is competitive with state-of-the-art large multilingual models. We build a clean, high-quality textual Catalan corpus (CaText), train a Transformer-based language model for Catalan (BERTa), and devise a thorough evaluation in a diversity of settings. The result is a new benchmark, the Catalan Language Understanding Benchmark (CLUB), which we publish as an open resource.
  arXiv  Detail & Related papers  (2021-07-16T13:52:01Z)
• Specializing Multilingual Language Models: An Empirical Study [50.7526245872855]
  Contextualized word representations from pretrained multilingual language models have become the de facto standard for addressing natural language tasks. For languages rarely or never seen by these models, directly using such models often results in suboptimal representation or use of data.
  arXiv  Detail & Related papers  (2021-06-16T18:13:55Z)
• TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing [73.16475763422446]
  We propose a multilingual robustness evaluation platform for NLP tasks (TextFlint) It incorporates universal text transformation, task-specific transformation, adversarial attack, subpopulation, and their combinations to provide comprehensive robustness analysis. TextFlint generates complete analytical reports as well as targeted augmented data to address the shortcomings of the model's robustness.
  arXiv  Detail & Related papers  (2021-03-21T17:20:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.