@inproceedings{franklin-etal-2024-news,
title = "News Deja Vu: Connecting Past and Present with Semantic Search",
author = "Franklin, Brevin and
Silcock, Emily and
Arora, Abhishek and
Bryan, Tom and
Dell, Melissa",
editor = "Card, Dallas and
Field, Anjalie and
Hovy, Dirk and
Keith, Katherine",
booktitle = "Proceedings of the Sixth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.nlpcss-1.8",
doi = "10.18653/v1/2024.nlpcss-1.8",
pages = "99--112",
abstract = "Social scientists and the general public often analyze contemporary events by drawing parallels with the past, a process complicated by the vast, noisy, and unstructured nature of historical texts. For example, hundreds of millions of page scans from historical newspapers have been noisily transcribed. Traditional sparse methods for searching for relevant material in these vast corpora, e.g., with keywords, can be brittle given complex vocabularies and OCR noise. This study introduces News Deja Vu, a novel semantic search tool that leverages transformer large language models and a bi-encoder approach to identify historical news articles that are most similar to modern news queries. News Deja Vu first recognizes and masks entities, in order to focus on broader parallels rather than the specific named entities being discussed. Then, a contrastively trained, lightweight bi-encoder retrieves historical articles that are most similar semantically to a modern query, illustrating how phenomena that might seem unique to the present have varied historical precedents. Aimed at social scientists, the user-friendly News Deja Vu package is designed to be accessible for those who lack extensive familiarity with deep learning. It works with large text datasets, and we show how it can be deployed to a massive scale corpus of historical, open-source news articles. While human expertise remains important for drawing deeper insights, News Deja Vu provides a powerful tool for exploring parallels in how people have perceived past and present.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="franklin-etal-2024-news">
<titleInfo>
<title>News Deja Vu: Connecting Past and Present with Semantic Search</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brevin</namePart>
<namePart type="family">Franklin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Silcock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhishek</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Bryan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melissa</namePart>
<namePart type="family">Dell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dallas</namePart>
<namePart type="family">Card</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anjalie</namePart>
<namePart type="family">Field</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katherine</namePart>
<namePart type="family">Keith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Social scientists and the general public often analyze contemporary events by drawing parallels with the past, a process complicated by the vast, noisy, and unstructured nature of historical texts. For example, hundreds of millions of page scans from historical newspapers have been noisily transcribed. Traditional sparse methods for searching for relevant material in these vast corpora, e.g., with keywords, can be brittle given complex vocabularies and OCR noise. This study introduces News Deja Vu, a novel semantic search tool that leverages transformer large language models and a bi-encoder approach to identify historical news articles that are most similar to modern news queries. News Deja Vu first recognizes and masks entities, in order to focus on broader parallels rather than the specific named entities being discussed. Then, a contrastively trained, lightweight bi-encoder retrieves historical articles that are most similar semantically to a modern query, illustrating how phenomena that might seem unique to the present have varied historical precedents. Aimed at social scientists, the user-friendly News Deja Vu package is designed to be accessible for those who lack extensive familiarity with deep learning. It works with large text datasets, and we show how it can be deployed to a massive scale corpus of historical, open-source news articles. While human expertise remains important for drawing deeper insights, News Deja Vu provides a powerful tool for exploring parallels in how people have perceived past and present.</abstract>
<identifier type="citekey">franklin-etal-2024-news</identifier>
<identifier type="doi">10.18653/v1/2024.nlpcss-1.8</identifier>
<location>
<url>https://aclanthology.org/2024.nlpcss-1.8</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>99</start>
<end>112</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T News Deja Vu: Connecting Past and Present with Semantic Search
%A Franklin, Brevin
%A Silcock, Emily
%A Arora, Abhishek
%A Bryan, Tom
%A Dell, Melissa
%Y Card, Dallas
%Y Field, Anjalie
%Y Hovy, Dirk
%Y Keith, Katherine
%S Proceedings of the Sixth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F franklin-etal-2024-news
%X Social scientists and the general public often analyze contemporary events by drawing parallels with the past, a process complicated by the vast, noisy, and unstructured nature of historical texts. For example, hundreds of millions of page scans from historical newspapers have been noisily transcribed. Traditional sparse methods for searching for relevant material in these vast corpora, e.g., with keywords, can be brittle given complex vocabularies and OCR noise. This study introduces News Deja Vu, a novel semantic search tool that leverages transformer large language models and a bi-encoder approach to identify historical news articles that are most similar to modern news queries. News Deja Vu first recognizes and masks entities, in order to focus on broader parallels rather than the specific named entities being discussed. Then, a contrastively trained, lightweight bi-encoder retrieves historical articles that are most similar semantically to a modern query, illustrating how phenomena that might seem unique to the present have varied historical precedents. Aimed at social scientists, the user-friendly News Deja Vu package is designed to be accessible for those who lack extensive familiarity with deep learning. It works with large text datasets, and we show how it can be deployed to a massive scale corpus of historical, open-source news articles. While human expertise remains important for drawing deeper insights, News Deja Vu provides a powerful tool for exploring parallels in how people have perceived past and present.
%R 10.18653/v1/2024.nlpcss-1.8
%U https://aclanthology.org/2024.nlpcss-1.8
%U https://doi.org/10.18653/v1/2024.nlpcss-1.8
%P 99-112
Markdown (Informal)
[News Deja Vu: Connecting Past and Present with Semantic Search](https://aclanthology.org/2024.nlpcss-1.8) (Franklin et al., NLP+CSS-WS 2024)
ACL
- Brevin Franklin, Emily Silcock, Abhishek Arora, Tom Bryan, and Melissa Dell. 2024. News Deja Vu: Connecting Past and Present with Semantic Search. In Proceedings of the Sixth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS 2024), pages 99–112, Mexico City, Mexico. Association for Computational Linguistics.