[Lions: 1] and [Tigers: 2] and [Bears: 3], Oh My! Literary Coreference Annotation with LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hicke, Rebecca M. M., Mimno, David
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916111240396800
author Hicke, Rebecca M. M.
Mimno, David
author_facet Hicke, Rebecca M. M.
Mimno, David
contents Coreference annotation and resolution is a vital component of computational literary studies. However, it has previously been difficult to build high quality systems for fiction. Coreference requires complicated structured outputs, and literary text involves subtle inferences and highly varied language. New language-model-based seq2seq systems present the opportunity to solve both these problems by learning to directly generate a copy of an input sentence with markdown-like annotations. We create, evaluate, and release several trained models for coreference, as well as a workflow for training new models.
format Preprint
id arxiv_https___arxiv_org_abs_2401_17922
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle [Lions: 1] and [Tigers: 2] and [Bears: 3], Oh My! Literary Coreference Annotation with LLMs
Hicke, Rebecca M. M.
Mimno, David
Computation and Language
Coreference annotation and resolution is a vital component of computational literary studies. However, it has previously been difficult to build high quality systems for fiction. Coreference requires complicated structured outputs, and literary text involves subtle inferences and highly varied language. New language-model-based seq2seq systems present the opportunity to solve both these problems by learning to directly generate a copy of an input sentence with markdown-like annotations. We create, evaluate, and release several trained models for coreference, as well as a workflow for training new models.
title [Lions: 1] and [Tigers: 2] and [Bears: 3], Oh My! Literary Coreference Annotation with LLMs
topic Computation and Language
url https://arxiv.org/abs/2401.17922