@inproceedings{lim-etal-2023-leaf,
title = "{LEAF}: Linguistically Enhanced Event Temporal Relation Framework",
author = "Lim, Stanley and
Yin, Da and
Peng, Nanyun",
editor = "Surdeanu, Mihai and
Riloff, Ellen and
Chiticariu, Laura and
Frietag, Dayne and
Hahn-Powell, Gus and
Morrison, Clayton T. and
Noriega-Atala, Enrique and
Sharp, Rebecca and
Valenzuela-Escarcega, Marco",
booktitle = "Proceedings of the 2nd Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.pandl-1.2",
doi = "10.18653/v1/2023.pandl-1.2",
pages = "6--19",
abstract = "Linguistic structures can implicitly imply diverse types of event relations that have been previously underexplored. For example, the sentence {``}John was cooking freshly made noodles for the family gathering{''} contains no explicit temporal indicators between the events, such as before. Despite this, it is easy for humans to conclude, based on syntax, that the noodles were made before John started cooking, and that the family gathering starts after John starts cooking. We introduce Linguistically enhanced Event TemporAl relation Framework (LEAF), a simple and effective approach to acquiring rich temporal knowledge of events from large-scale corpora. This method improves pre-trained language models by automatically extracting temporal relation knowledge from unannotated corpora using diverse temporal knowledge patterns. We begin by manually curating a comprehensive list of atomic patterns that imply temporal relations between events. These patterns involve event pairs in which one event is contained within the argument of the other. Using transitivity, we discover compositional patterns and assign labels to event pairs involving these patterns. Finally, we make language models learn the rich knowledge by pre-training with the acquired temporal relation supervision. Experiments show that our method outperforms or rivals previous models on two event relation datasets: MATRES and TB-Dense. Our approach is also simpler from past works and excels at identifying complex compositional event relations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lim-etal-2023-leaf">
<titleInfo>
<title>LEAF: Linguistically Enhanced Event Temporal Relation Framework</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stanley</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Da</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mihai</namePart>
<namePart type="family">Surdeanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Chiticariu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayne</namePart>
<namePart type="family">Frietag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gus</namePart>
<namePart type="family">Hahn-Powell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clayton</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Morrison</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrique</namePart>
<namePart type="family">Noriega-Atala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Sharp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Valenzuela-Escarcega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Linguistic structures can implicitly imply diverse types of event relations that have been previously underexplored. For example, the sentence “John was cooking freshly made noodles for the family gathering” contains no explicit temporal indicators between the events, such as before. Despite this, it is easy for humans to conclude, based on syntax, that the noodles were made before John started cooking, and that the family gathering starts after John starts cooking. We introduce Linguistically enhanced Event TemporAl relation Framework (LEAF), a simple and effective approach to acquiring rich temporal knowledge of events from large-scale corpora. This method improves pre-trained language models by automatically extracting temporal relation knowledge from unannotated corpora using diverse temporal knowledge patterns. We begin by manually curating a comprehensive list of atomic patterns that imply temporal relations between events. These patterns involve event pairs in which one event is contained within the argument of the other. Using transitivity, we discover compositional patterns and assign labels to event pairs involving these patterns. Finally, we make language models learn the rich knowledge by pre-training with the acquired temporal relation supervision. Experiments show that our method outperforms or rivals previous models on two event relation datasets: MATRES and TB-Dense. Our approach is also simpler from past works and excels at identifying complex compositional event relations.</abstract>
<identifier type="citekey">lim-etal-2023-leaf</identifier>
<identifier type="doi">10.18653/v1/2023.pandl-1.2</identifier>
<location>
<url>https://aclanthology.org/2023.pandl-1.2</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>6</start>
<end>19</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LEAF: Linguistically Enhanced Event Temporal Relation Framework
%A Lim, Stanley
%A Yin, Da
%A Peng, Nanyun
%Y Surdeanu, Mihai
%Y Riloff, Ellen
%Y Chiticariu, Laura
%Y Frietag, Dayne
%Y Hahn-Powell, Gus
%Y Morrison, Clayton T.
%Y Noriega-Atala, Enrique
%Y Sharp, Rebecca
%Y Valenzuela-Escarcega, Marco
%S Proceedings of the 2nd Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F lim-etal-2023-leaf
%X Linguistic structures can implicitly imply diverse types of event relations that have been previously underexplored. For example, the sentence “John was cooking freshly made noodles for the family gathering” contains no explicit temporal indicators between the events, such as before. Despite this, it is easy for humans to conclude, based on syntax, that the noodles were made before John started cooking, and that the family gathering starts after John starts cooking. We introduce Linguistically enhanced Event TemporAl relation Framework (LEAF), a simple and effective approach to acquiring rich temporal knowledge of events from large-scale corpora. This method improves pre-trained language models by automatically extracting temporal relation knowledge from unannotated corpora using diverse temporal knowledge patterns. We begin by manually curating a comprehensive list of atomic patterns that imply temporal relations between events. These patterns involve event pairs in which one event is contained within the argument of the other. Using transitivity, we discover compositional patterns and assign labels to event pairs involving these patterns. Finally, we make language models learn the rich knowledge by pre-training with the acquired temporal relation supervision. Experiments show that our method outperforms or rivals previous models on two event relation datasets: MATRES and TB-Dense. Our approach is also simpler from past works and excels at identifying complex compositional event relations.
%R 10.18653/v1/2023.pandl-1.2
%U https://aclanthology.org/2023.pandl-1.2
%U https://doi.org/10.18653/v1/2023.pandl-1.2
%P 6-19
Markdown (Informal)
[LEAF: Linguistically Enhanced Event Temporal Relation Framework](https://aclanthology.org/2023.pandl-1.2) (Lim et al., PANDL-WS 2023)
ACL