Saved in:
Bibliographic Details
Main Authors: Bhowmik, Rajarshi, Ponza, Marco, Tendle, Atharva, Gupta, Anant, Jiang, Rebecca, Lu, Xingyu, Zhao, Qian, Preotiuc-Pietro, Daniel
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2309.07990
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914738712084480
author Bhowmik, Rajarshi
Ponza, Marco
Tendle, Atharva
Gupta, Anant
Jiang, Rebecca
Lu, Xingyu
Zhao, Qian
Preotiuc-Pietro, Daniel
author_facet Bhowmik, Rajarshi
Ponza, Marco
Tendle, Atharva
Gupta, Anant
Jiang, Rebecca
Lu, Xingyu
Zhao, Qian
Preotiuc-Pietro, Daniel
contents In text documents such as news articles, the content and key events usually revolve around a subset of all the entities mentioned in a document. These entities, often deemed as salient entities, provide useful cues of the aboutness of a document to a reader. Identifying the salience of entities was found helpful in several downstream applications such as search, ranking, and entity-centric summarization, among others. Prior work on salient entity detection mainly focused on machine learning models that require heavy feature engineering. We show that fine-tuning medium-sized language models with a cross-encoder style architecture yields substantial performance gains over feature engineering approaches. To this end, we conduct a comprehensive benchmarking of four publicly available datasets using models representative of the medium-sized pre-trained language model family. Additionally, we show that zero-shot prompting of instruction-tuned language models yields inferior results, indicating the task's uniqueness and complexity.
format Preprint
id arxiv_https___arxiv_org_abs_2309_07990
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Leveraging Contextual Information for Effective Entity Salience Detection
Bhowmik, Rajarshi
Ponza, Marco
Tendle, Atharva
Gupta, Anant
Jiang, Rebecca
Lu, Xingyu
Zhao, Qian
Preotiuc-Pietro, Daniel
Computation and Language
In text documents such as news articles, the content and key events usually revolve around a subset of all the entities mentioned in a document. These entities, often deemed as salient entities, provide useful cues of the aboutness of a document to a reader. Identifying the salience of entities was found helpful in several downstream applications such as search, ranking, and entity-centric summarization, among others. Prior work on salient entity detection mainly focused on machine learning models that require heavy feature engineering. We show that fine-tuning medium-sized language models with a cross-encoder style architecture yields substantial performance gains over feature engineering approaches. To this end, we conduct a comprehensive benchmarking of four publicly available datasets using models representative of the medium-sized pre-trained language model family. Additionally, we show that zero-shot prompting of instruction-tuned language models yields inferior results, indicating the task's uniqueness and complexity.
title Leveraging Contextual Information for Effective Entity Salience Detection
topic Computation and Language
url https://arxiv.org/abs/2309.07990