Portho: A Corpus-Based Resource of Orthographic Neighbors in European Portuguese

2026-04-12 · Source: Paper Index on ACL Anthology · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics, Social Sciences & Behavioral Studies · Depth: Expert, medium

Summary

Portho is a new corpus-based lexical resource for European Portuguese, introduced at the PROPOR 2026 conference, that provides detailed orthographic neighbor (ON) information for over 43,000 word forms. This resource includes multiple ON metrics, various ON definitions, classical neighborhood size measures, frequency-based statistics, and graded orthographic distance (OD) features. Researchers analyzed Portho's statistical properties and evaluated its effectiveness in automatic text complexity assessment using the iRead4Skills corpus. While ON features alone were not sufficient to predict readability, they offered complementary information and performed well compared to existing Portuguese resources. Portho is publicly available to support research in psycholinguistics, readability modeling, and Natural Language Processing (NLP) for Portuguese.

Key takeaway

For NLP engineers and psycholinguists working with European Portuguese, Portho offers a valuable, publicly available resource for orthographic neighbor analysis. You should integrate its detailed ON metrics and frequency-based statistics into your models to enhance research in visual word recognition, lexical access, and text complexity assessment, even though ON features alone may not fully predict readability.

Key insights

Portho provides comprehensive orthographic neighbor metrics for European Portuguese, aiding psycholinguistics and NLP.

Principles

• ONs influence reading speed and lexical access.
• ON features complement readability prediction.

Method

Portho was developed as a corpus-based lexical resource, providing ON metrics, frequency statistics, and graded OD features for over 43,000 word forms, then evaluated for text complexity assessment.

In practice

• Utilize Portho for psycholinguistic studies.
• Integrate ON features into readability models.
• Apply Portho in Portuguese NLP tasks.

Topics

• Portho
• Orthographic Neighbors
• European Portuguese
• Lexical Resource
• Text Complexity Assessment

Best for: AI Scientist, Research Scientist, NLP Engineer

Related on AIssential

• Dependency Distance Effects on Eye-Tracking Measures in Brazilian Portuguese — Absolute dependency distance significantly predicts early lexical retrieval in Brazilian Portuguese eye-tracking.
• RUMLEM: A Dictionary-Based Lemmatizer for Romansh — A dictionary-based lemmatizer for Romansh addresses NLP challenges for less-resourced languages.
• A Bolu: A Structured Dataset for the Computational Analysis of Sardinian Improvisational Poetry — A Bolu is the first structured corpus for analyzing Sardinian extemporaneous poetry, revealing formulaic patterns.
• PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction — Specialized multilingual data significantly improves European Portuguese OCR performance over model size or resolution.
• A Scalable Tool for Measuring Manner and Result Verbs in Developmental Language Research — A RoBERTa classifier, trained on LLM-generated annotations, accurately distinguishes manner and result verbs at scale.
• An End-to-End Hybrid Framework for Rumour Detection in Low-Resources Algerian Dialect — A hybrid framework combining transformer embeddings with classical classifiers enables effective rumour detection in low-resource Algerian dialect.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Paper Index on ACL Anthology.