@inproceedings{wang-etal-2025-temporal,
title = "Temporal-Aware Soft Prompt Tuning for Automatic Text Dating",
author = "Wang, Hai and
Liang, Yuzhi and
Ren, Han",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.200/",
doi = "10.18653/v1/2025.naacl-long.200",
pages = "3975--3987",
ISBN = "979-8-89176-189-6",
abstract = "This paper presents Temporal-aware Soft Prompt Tuning (TASPT), a novel approach for automatic text dating. Unlike existing methods, which often overlook the evolution of word meanings in texts spanning long periods, TASPT incorporates the unique characteristics of historical texts. It introduces a temporal-aware text representation that dynamically captures both semantic variance and invariance. This representation is combined with a soft prompt, enabling efficient parameter tuning for automatic text dating. Experiments show that TASPT outperforms all existing methods on two diachronic datasets: the Twenty-Four Histories and the Royal Society Corpus."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2025-temporal">
<titleInfo>
<title>Temporal-Aware Soft Prompt Tuning for Automatic Text Dating</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hai</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuzhi</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>This paper presents Temporal-aware Soft Prompt Tuning (TASPT), a novel approach for automatic text dating. Unlike existing methods, which often overlook the evolution of word meanings in texts spanning long periods, TASPT incorporates the unique characteristics of historical texts. It introduces a temporal-aware text representation that dynamically captures both semantic variance and invariance. This representation is combined with a soft prompt, enabling efficient parameter tuning for automatic text dating. Experiments show that TASPT outperforms all existing methods on two diachronic datasets: the Twenty-Four Histories and the Royal Society Corpus.</abstract>
<identifier type="citekey">wang-etal-2025-temporal</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.200</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.200/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>3975</start>
<end>3987</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Temporal-Aware Soft Prompt Tuning for Automatic Text Dating
%A Wang, Hai
%A Liang, Yuzhi
%A Ren, Han
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F wang-etal-2025-temporal
%X This paper presents Temporal-aware Soft Prompt Tuning (TASPT), a novel approach for automatic text dating. Unlike existing methods, which often overlook the evolution of word meanings in texts spanning long periods, TASPT incorporates the unique characteristics of historical texts. It introduces a temporal-aware text representation that dynamically captures both semantic variance and invariance. This representation is combined with a soft prompt, enabling efficient parameter tuning for automatic text dating. Experiments show that TASPT outperforms all existing methods on two diachronic datasets: the Twenty-Four Histories and the Royal Society Corpus.
%R 10.18653/v1/2025.naacl-long.200
%U https://aclanthology.org/2025.naacl-long.200/
%U https://doi.org/10.18653/v1/2025.naacl-long.200
%P 3975-3987
Markdown (Informal)
[Temporal-Aware Soft Prompt Tuning for Automatic Text Dating](https://aclanthology.org/2025.naacl-long.200/) (Wang et al., NAACL 2025)
ACL
- Hai Wang, Yuzhi Liang, and Han Ren. 2025. Temporal-Aware Soft Prompt Tuning for Automatic Text Dating. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 3975–3987, Albuquerque, New Mexico. Association for Computational Linguistics.