Cited Text Spans for Citation Text Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xiangci, Lee, Yi-Hui, Ouyang, Jessica
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910946517057536
author Li, Xiangci
Lee, Yi-Hui
Ouyang, Jessica
author_facet Li, Xiangci
Lee, Yi-Hui
Ouyang, Jessica
contents An automatic citation generation system aims to concisely and accurately describe the relationship between two scientific articles. To do so, such a system must ground its outputs to the content of the cited paper to avoid non-factual hallucinations. Due to the length of scientific documents, existing abstractive approaches have conditioned only on cited paper abstracts. We demonstrate empirically that the abstract is not always the most appropriate input for citation generation and that models trained in this way learn to hallucinate. We propose to condition instead on the cited text span (CTS) as an alternative to the abstract. Because manual CTS annotation is extremely time- and labor-intensive, we experiment with distant labeling of candidate CTS sentences, achieving sufficiently strong performance to substitute for expensive human annotations in model training, and we propose a human-in-the-loop, keyword-based CTS retrieval approach that makes generating citation texts grounded in the full text of cited papers both promising and practical.
format Preprint
id arxiv_https___arxiv_org_abs_2309_06365
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Cited Text Spans for Citation Text Generation
Li, Xiangci
Lee, Yi-Hui
Ouyang, Jessica
Computation and Language
An automatic citation generation system aims to concisely and accurately describe the relationship between two scientific articles. To do so, such a system must ground its outputs to the content of the cited paper to avoid non-factual hallucinations. Due to the length of scientific documents, existing abstractive approaches have conditioned only on cited paper abstracts. We demonstrate empirically that the abstract is not always the most appropriate input for citation generation and that models trained in this way learn to hallucinate. We propose to condition instead on the cited text span (CTS) as an alternative to the abstract. Because manual CTS annotation is extremely time- and labor-intensive, we experiment with distant labeling of candidate CTS sentences, achieving sufficiently strong performance to substitute for expensive human annotations in model training, and we propose a human-in-the-loop, keyword-based CTS retrieval approach that makes generating citation texts grounded in the full text of cited papers both promising and practical.
title Cited Text Spans for Citation Text Generation
topic Computation and Language
url https://arxiv.org/abs/2309.06365