@inproceedings{mathur-etal-2024-docscript,
title = "{D}oc{S}cript: Document-level Script Event Prediction",
author = "Mathur, Puneet and
Morariu, Vlad I. and
Garimella, Aparna and
Dernoncourt, Franck and
Gu, Jiuxiang and
Sawhney, Ramit and
Nakov, Preslav and
Manocha, Dinesh and
Jain, Rajiv",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.458",
pages = "5140--5155",
abstract = "We present a novel task of document-level script event prediction, which aims to predict the next event given a candidate list of narrative events in long-form documents. To enable this, we introduce DocSEP, a challenging dataset in two new domains - contractual documents and Wikipedia articles, where timeline events may be paragraphs apart and may require multi-hop temporal and causal reasoning. We benchmark existing baselines and present a novel architecture called DocScript to learn sequential ordering between events at the document scale. Our experimental results on the DocSEP dataset demonstrate that learning longer-range dependencies between events is a key challenge and show that contemporary LLMs such as ChatGPT and FlanT5 struggle to solve this task, indicating their lack of reasoning abilities for understanding causal relationships and temporal sequences within long texts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mathur-etal-2024-docscript">
<titleInfo>
<title>DocScript: Document-level Script Event Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Puneet</namePart>
<namePart type="family">Mathur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vlad</namePart>
<namePart type="given">I</namePart>
<namePart type="family">Morariu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aparna</namePart>
<namePart type="family">Garimella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiuxiang</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramit</namePart>
<namePart type="family">Sawhney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dinesh</namePart>
<namePart type="family">Manocha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajiv</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a novel task of document-level script event prediction, which aims to predict the next event given a candidate list of narrative events in long-form documents. To enable this, we introduce DocSEP, a challenging dataset in two new domains - contractual documents and Wikipedia articles, where timeline events may be paragraphs apart and may require multi-hop temporal and causal reasoning. We benchmark existing baselines and present a novel architecture called DocScript to learn sequential ordering between events at the document scale. Our experimental results on the DocSEP dataset demonstrate that learning longer-range dependencies between events is a key challenge and show that contemporary LLMs such as ChatGPT and FlanT5 struggle to solve this task, indicating their lack of reasoning abilities for understanding causal relationships and temporal sequences within long texts.</abstract>
<identifier type="citekey">mathur-etal-2024-docscript</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.458</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>5140</start>
<end>5155</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DocScript: Document-level Script Event Prediction
%A Mathur, Puneet
%A Morariu, Vlad I.
%A Garimella, Aparna
%A Dernoncourt, Franck
%A Gu, Jiuxiang
%A Sawhney, Ramit
%A Nakov, Preslav
%A Manocha, Dinesh
%A Jain, Rajiv
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F mathur-etal-2024-docscript
%X We present a novel task of document-level script event prediction, which aims to predict the next event given a candidate list of narrative events in long-form documents. To enable this, we introduce DocSEP, a challenging dataset in two new domains - contractual documents and Wikipedia articles, where timeline events may be paragraphs apart and may require multi-hop temporal and causal reasoning. We benchmark existing baselines and present a novel architecture called DocScript to learn sequential ordering between events at the document scale. Our experimental results on the DocSEP dataset demonstrate that learning longer-range dependencies between events is a key challenge and show that contemporary LLMs such as ChatGPT and FlanT5 struggle to solve this task, indicating their lack of reasoning abilities for understanding causal relationships and temporal sequences within long texts.
%U https://aclanthology.org/2024.lrec-main.458
%P 5140-5155
Markdown (Informal)
[DocScript: Document-level Script Event Prediction](https://aclanthology.org/2024.lrec-main.458) (Mathur et al., LREC-COLING 2024)
ACL
- Puneet Mathur, Vlad I. Morariu, Aparna Garimella, Franck Dernoncourt, Jiuxiang Gu, Ramit Sawhney, Preslav Nakov, Dinesh Manocha, and Rajiv Jain. 2024. DocScript: Document-level Script Event Prediction. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5140–5155, Torino, Italia. ELRA and ICCL.