Saved in:
Bibliographic Details
Main Authors: Song, Mingyang, Feng, Yi, Jing, Liping
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.16571
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914812858990592
author Song, Mingyang
Feng, Yi
Jing, Liping
author_facet Song, Mingyang
Feng, Yi
Jing, Liping
contents Pre-trained large language models can perform natural language processing downstream tasks by conditioning on human-designed prompts. However, a prompt-based approach often requires "prompt engineering" to design different prompts, primarily hand-crafted through laborious trial and error, requiring human intervention and expertise. It is a challenging problem when constructing a prompt-based keyphrase extraction method. Therefore, we investigate and study the effectiveness of different prompts on the keyphrase extraction task to verify the impact of the cherry-picked prompts on the performance of extracting keyphrases. Extensive experimental results on six benchmark keyphrase extraction datasets and different pre-trained large language models demonstrate that (1) designing complex prompts may not necessarily be more effective than designing simple prompts; (2) individual keyword changes in the designed prompts can affect the overall performance; (3) designing complex prompts achieve better performance than designing simple prompts when facing long documents.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16571
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Preliminary Empirical Study on Prompt-based Unsupervised Keyphrase Extraction
Song, Mingyang
Feng, Yi
Jing, Liping
Computation and Language
Pre-trained large language models can perform natural language processing downstream tasks by conditioning on human-designed prompts. However, a prompt-based approach often requires "prompt engineering" to design different prompts, primarily hand-crafted through laborious trial and error, requiring human intervention and expertise. It is a challenging problem when constructing a prompt-based keyphrase extraction method. Therefore, we investigate and study the effectiveness of different prompts on the keyphrase extraction task to verify the impact of the cherry-picked prompts on the performance of extracting keyphrases. Extensive experimental results on six benchmark keyphrase extraction datasets and different pre-trained large language models demonstrate that (1) designing complex prompts may not necessarily be more effective than designing simple prompts; (2) individual keyword changes in the designed prompts can affect the overall performance; (3) designing complex prompts achieve better performance than designing simple prompts when facing long documents.
title A Preliminary Empirical Study on Prompt-based Unsupervised Keyphrase Extraction
topic Computation and Language
url https://arxiv.org/abs/2405.16571