My draft's characters all sound the same. What simple check can I run to confirm it and find which lines to fix?
Baker (1919) gives two manual checks that need no software: swap each speaker label for a bare type name ('A man', 'A young woman') and see whether the dialogue still identifies who is speaking, and ask of each speech whether the imagined speaker, not the author, would say it. The computational papers add automatic versions of the first idea: if a classifier cannot tell speakers apart from their lines, or character-vs-rest distance is near the self-baseline, the voices are not distinct. No source gives a pass mark for a draft.
Baker (1919) gives two manual checks that need no software: swap each speaker label for a bare type name ('A man', 'A young woman') and see whether the dialogue still identifies who is speaking, and ask of each speech whether the imagined speaker, not the author, would say it. The computational papers add automatic versions of the first idea: if a classifier cannot tell speakers apart from their lines, or character-vs-rest distance is near the self-baseline, the voices are not distinct. No source gives a pass mark for a draft.
Curator qualifications: Verified that the Baker checks exist. The candidate correctly labels using the label-swap test for distinctness as its own adaptation, since Baker uses it for identifiability.
Evidence status: statements located in the cited sources by a correlated desk review (Claude); not executed; not independently reviewed.
Structured fields
{
"citations": [
{
"url": "https://www.gutenberg.org/cache/epub/36580/pg36580.txt",
"note": "label-swap and author-intrusion passages"
},
{
"url": "https://aclanthology.org/W19-2504.pdf",
"note": "label-swap and author-intrusion passages"
},
{
"url": "https://arxiv.org/abs/2301.05659v1",
"note": "label-swap and author-intrusion passages"
}
]
}Evidence claims
- [sourced_fact] Baker (1919) gives two manual checks that need no software: swap each speaker label for a bare type name ('A man', 'A young woman') and see whether the dialogue still identifies who is speaking, and ask of each speech whether the imagined speaker, not the author, would say it. The computational papers add automatic versions of the first idea: if a classifier cannot tell speakers apart from their lines, or character-vs-rest distance is near the self-baseline, the voices are not distinct. No source gives a pass mark for a draft. · locator: label-swap and author-intrusion passages source
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| documentation | unknown | permitted | permitted | unknown | unknown | Applies to this original summary only, not to the cited sources. |