@inproceedings{marfurt-etal-2024-generating,
title = "Generating Interpretations of Policy Announcements",
author = "Marfurt, Andreas and
Thornton, Ashley and
Sylvan, David and
Henderson, James",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
{\"O}hman, Emily and
Miyagawa, So and
Alnajjar, Khalid and
Bizzoni, Yuri},
booktitle = "Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities",
month = nov,
year = "2024",
address = "Miami, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.nlp4dh-1.50",
pages = "513--520",
abstract = "Recent advances in language modeling have focused on (potentially multiple-choice) question answering, open-ended generation, or math and coding problems. We look at a more nuanced task: the interpretation of statements of political actors. To this end, we present a dataset of policy announcements and corresponding annotated interpretations, on the topic of US foreign policy relations with Russia in the years 1993 up to 2016. We analyze the performance of finetuning standard sequence-to-sequence models of varying sizes on predicting the annotated interpretations and compare them to few-shot prompted large language models. We find that 1) model size is not the main factor for success on this task, 2) finetuning smaller models provides both quantitatively and qualitatively superior results to in-context learning with large language models, but 3) large language models pick up the annotation format and approximate the category distribution with just a few in-context examples.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marfurt-etal-2024-generating">
<titleInfo>
<title>Generating Interpretations of Policy Announcements</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Marfurt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashley</namePart>
<namePart type="family">Thornton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Sylvan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Henderson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">So</namePart>
<namePart type="family">Miyagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in language modeling have focused on (potentially multiple-choice) question answering, open-ended generation, or math and coding problems. We look at a more nuanced task: the interpretation of statements of political actors. To this end, we present a dataset of policy announcements and corresponding annotated interpretations, on the topic of US foreign policy relations with Russia in the years 1993 up to 2016. We analyze the performance of finetuning standard sequence-to-sequence models of varying sizes on predicting the annotated interpretations and compare them to few-shot prompted large language models. We find that 1) model size is not the main factor for success on this task, 2) finetuning smaller models provides both quantitatively and qualitatively superior results to in-context learning with large language models, but 3) large language models pick up the annotation format and approximate the category distribution with just a few in-context examples.</abstract>
<identifier type="citekey">marfurt-etal-2024-generating</identifier>
<location>
<url>https://aclanthology.org/2024.nlp4dh-1.50</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>513</start>
<end>520</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Interpretations of Policy Announcements
%A Marfurt, Andreas
%A Thornton, Ashley
%A Sylvan, David
%A Henderson, James
%Y Hämäläinen, Mika
%Y Öhman, Emily
%Y Miyagawa, So
%Y Alnajjar, Khalid
%Y Bizzoni, Yuri
%S Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, USA
%F marfurt-etal-2024-generating
%X Recent advances in language modeling have focused on (potentially multiple-choice) question answering, open-ended generation, or math and coding problems. We look at a more nuanced task: the interpretation of statements of political actors. To this end, we present a dataset of policy announcements and corresponding annotated interpretations, on the topic of US foreign policy relations with Russia in the years 1993 up to 2016. We analyze the performance of finetuning standard sequence-to-sequence models of varying sizes on predicting the annotated interpretations and compare them to few-shot prompted large language models. We find that 1) model size is not the main factor for success on this task, 2) finetuning smaller models provides both quantitatively and qualitatively superior results to in-context learning with large language models, but 3) large language models pick up the annotation format and approximate the category distribution with just a few in-context examples.
%U https://aclanthology.org/2024.nlp4dh-1.50
%P 513-520
Markdown (Informal)
[Generating Interpretations of Policy Announcements](https://aclanthology.org/2024.nlp4dh-1.50) (Marfurt et al., NLP4DH 2024)
ACL
- Andreas Marfurt, Ashley Thornton, David Sylvan, and James Henderson. 2024. Generating Interpretations of Policy Announcements. In Proceedings of the 4th International Conference on Natural Language Processing for Digital Humanities, pages 513–520, Miami, USA. Association for Computational Linguistics.