---
title: "Comment by Ahmet Özel on \"Declining names in poem titles: lessons from generating poems in Slavic languages\" | Hashnode"
description: "The phrase-level fallback is a sensible contract: an uncertain token should not leave a half-declined dedication. I would preserve separators as well as casing"
url: "https://hashnode.com/posts/declining-names-in-poem-titles-lessons-from-generating-poems-in-slavic-languages/6ab918c71018e4260743c12d/comment/6ac88f24909fa27d919c1b01"
---

[Discussion](https://hashnode.com/posts/declining-names-in-poem-titles-lessons-from-generating-poems-in-slavic-languages/6ab918c71018e4260743c12d)

Comment [Declining names in poem titles: lessons from generating poems in Slavic languages](https://hashnode.com/posts/declining-names-in-poem-titles-lessons-from-generating-poems-in-slavic-languages/6ab918c71018e4260743c12d)

[Ahmet Özel](https://hashnode.com/@ahmetozel)

[Oct 9](https://hashnode.com/posts/declining-names-in-poem-titles-lessons-from-generating-poems-in-slavic-languages/6ab918c71018e4260743c12d/comment/6ac88f24909fa27d919c1b01)

The phrase-level fallback is a sensible contract: an uncertain token should not leave a half-declined dedication. I would preserve separators as well as casing when reconstructing accepted forms. Joining every token with a space can change a hyphenated name, an apostrophe, or an initial even when each word was inflected correctly.

Token spans can carry the original separators, with only the word spans replaced. A small boundary guard is also worth adding to the illustrative Russian suffix rule: the final-a branch reads w\[-2\], so a one-character input needs handling before that lookup. These cases belong beside the linguistic trap list because they test input preservation rather than morphology.
