EvaluatedApplications.Prose 1.0.0

Prose

A grammar-driven synthetic corpus generator for .NET. Prose reads plain text through the rules of grammar, keeps what it learns in a HoloDb database, and recombines it into new sentences that are grammatical, use words suited to their slots, and read plausibly. It exists to grow a training corpus: mine the knowledge already in your text, then generate more of it.

It works the way a person who has learned grammar does — find the subject, the verb, which adjectives modify which noun — rather than by pasting fragments together. No word is locked to one role: shoots is a noun after "bamboo" and a verb after "panda", decided by context. The canonical example is Eats, Shoots & Leaves: the comma changes the parse, and the meaning with it.

Pipeline

1. Parse (rules, zero training). Sentence splitting, a closed-class + morphology + distributional POS tagger, phrase chunking, and role assignment (subject, coordinate finite verbs, objects, copular predicate).
2. Mine → HoloDb. A lexicon, subject→verb / verb→object / adjective→noun selectional tables, syntax templates and bigrams, written with BulkLoad.
3. Generate. Sample a clause shape from the mined templates, fill each slot with a word that is the right category, suitable (respects the selectional tables) and plausible, realize it with correct agreement (a/an, subject–verb), and emit only sentences that pass a validity gate (which re-parses each candidate).
4. Plausibility (optional). A small HoloFormer language model over content-word lemmas ranks candidates so meaning improves while grammar stays guaranteed.
5. Q&A pairs. Because each generated sentence keeps its role structure (subject / verb / object / predicate), Prose emits reading-comprehension pairs — a context, a question, and the answer derivable from it — as a prompt\ttarget TSV. This includes multi-sentence passages whose sentences reuse the same entities (definite references and pronouns), so questions refer back across the passage and answers require coreference — long-context training data.

Usage

var prose = new ProseEngine();
prose.Mine(@"C:\corpus\text");                 // parse every *.txt and mine it
prose.Save(@"prose.wal");                        // persist the tables to HoloDb (optional)

prose.TrainPlausibility(@"C:\corpus\text");      // optional mini-HoloFormer scorer

foreach (var sentence in prose.Generate(1000))   // new, grammatical, plausible sentences
    Console.WriteLine(sentence);

prose.WriteCorpus(@"C:\corpus\synthetic", 100_000);   // write them out as .txt for an LM
prose.WriteQaPairs(@"C:\corpus\qa", 50_000);           // context+question -> answer, as prompt\ttarget TSV

Parse a single sentence directly:

var p = ProseEngine.ParseSentence("The panda eats, shoots, and leaves.");
Console.WriteLine(ProseEngine.Explain(p));   // subject, verbs, objects, template

License

Proprietary — this package ships the compiled library only; source is not distributed. Every capability in it is free to use. See LICENSE. Copyright (c) 2026 Dongyang Stephen Chen, trading as Evaluated Applications. All rights reserved.