SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.03754 · EMNLP · 2021

Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form Stories

Frank Keller, David Wilmot

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Measuring event salience is essential in the understanding of stories. This paper takes a recent unsupervised method for salience detection derived from Barthes Cardinal Functions and theories of surprise and applies it to longer narrative forms. We improve the standard transformer language model by incorporating an external knowledgebase (derived from Retrieval Augmented Generation) and adding a memory mechanism to enhance performance on longer works. We use a novel approach to derive salience annotation using chapteraligned summaries from the Shmoop corpus for classic literary works. Our evaluation against this data demonstrates that our salience detection model improves performance over and above a non-knowledgebase and memory augmented language model, both of which are crucial to this improvement.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2109.03754")
get_code_for_paper("2109.03754")
have("2109.03754")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2109.03754.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2109.03754.svg)](https://syntology.ai/paper/2109.03754)

Connect an agent — have() is free.