Annotated English

José Hernández-OralloarXiv 2010 · arXiv

Abstract

English orthography is notoriously irregular, posing significant challenges for learners and automated systems. Traditional spelling reforms often fail by breaking the visual and etymological link to existing literature. This paper proposes Annotated English, a system of diacritical marks that renders English pronunciation 100% unambiguous while preserving original spellings. By implementing a "Rule-Annotation Trade-off," the system minimizes visual clutter, achieving an annotation density comparable to naturally phonetic languages like Polish.

Introduction

The "Great Vowel Shift" and extensive linguistic borrowing have left English with a "deep" orthography where spelling often fails to map clearly to sound. Historical solutions typically fall into two categories: radical spelling reform (e.g., "skool" for "school"), which renders existing literature obsolete, or phonetic transcription (e.g., IPA), which is too dense for general reading. Annotated English seeks a "middle way"—a phonetic layer that preserves the visual identity and etymology of the language.

Methodology: The Rule-Annotation Trade-off

The core innovation of Annotated English is the use of "by-default" rules to handle common patterns, reserving diacritics only for exceptions. This approach minimizes the cognitive load on the reader and reduces visual noise.

The 12-Step Interpretation Pipeline

To convert an annotated word into its phonetic representation, the system follows a deterministic 12-step process, ranging from discarding silent letters and parsing digraphs to evaluating vowel/consonant units and post-processing for dialect-specific mergers.

Cost Optimization

To ensure the most efficient annotation, the author introduces a cost-weighting approach. Different marks (stress, silent letters, separators) are assigned specific "costs." An automated annotator uses dynamic programming to select the set of marks that achieves the correct pronunciation with the lowest total "cost," resulting in the cleanest possible text.

Comparison of text annotation density with and without default rules.

As shown in the figure above, the application of rules drastically reduces the number of required marks, making the text significantly more readable while retaining full phonetic information.

Results and Analysis

The system was evaluated using high-frequency word lists and literary excerpts, such as Dickens’ A Tale of Two Cities.

  • Annotation Density: In standard prose, the system requires approximately one annotation per 12 letters, or roughly one per three words.
  • Comparative Regularity: This density makes Annotated English as "regular" as Polish (1/12) and more regular than Czech (1/9), languages often cited for their phonetic consistency.
  • Etymological Preservation: Unlike spelling reform, Annotated English maintains the visual link between related words (e.g., sign and signal), which is crucial for vocabulary acquisition and historical understanding.

Discussion and Future Work

Annotated English offers a flexible framework that can be adapted to different dialects (e.g., General American vs. Received Pronunciation) without changing the underlying text. While the current system handles most irregularities, homographs (e.g., "read" vs. "read") still require semantic context for perfect annotation. Future work will focus on developing robust automated annotation software and conducting pedagogical studies to determine the system's effectiveness in literacy education.

Summary updated

Abstract

This document presents Annotated English, a system of diacritical symbols which turns English pronunciation into a precise and unambiguous process. The annotations are defined and located in such a way that the original English text is not altered (not even a letter), thus allowing for a consistent reading and learning of the English language with and without annotations. The annotations are based on a set of general rules that make the frequency of annotations not dramatically high. This makes the reader easily associate annotations with exceptions, and makes it possible to shape, internalise and consolidate some rules for the English language which otherwise are weakened by the enormous amount of exceptions in English pronunciation. The advantages of this annotation system are manifold. Any existing text can be annotated without a significant increase in size. This means that we can get an annotated version of any document or book with the same number of pages and fontsize. Since no letter is affected, the text can be perfectly read by a person who does not know the annotation rules, since annotations can be simply ignored. The annotations are based on a set of rules which can be progressively learned and recognised, even in cases where the reader has no access or time to read the rules. This means that a reader can understand most of the annotations after reading a few pages of Annotated English, and can take advantage from that knowledge for any other annotated document she may read in the future.
BibTeX
@misc{hernandezorallo2010annotated,
  author = {José Hernández-Orallo},
  title = {{Annotated English}},
  year = {2010},
  eprint = {1012.5962},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1012.5962},
}
Figure