@inproceedings{eisenberg-sheriff-2020-automatic,
title = "Automatic extraction of personal events from dialogue",
author = "Eisenberg, Joshua and
Sheriff, Michael",
editor = "Bonial, Claire and
Caselli, Tommaso and
Chaturvedi, Snigdha and
Clark, Elizabeth and
Huang, Ruihong and
Iyyer, Mohit and
Jaimes, Alejandro and
Ji, Heng and
Martin, Lara J. and
Miller, Ben and
Mitamura, Teruko and
Peng, Nanyun and
Tetreault, Joel",
booktitle = "Proceedings of the First Joint Workshop on Narrative Understanding, Storylines, and Events",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.nuse-1.8",
doi = "10.18653/v1/2020.nuse-1.8",
pages = "63--71",
abstract = "In this paper we introduce the problem of extracting events from dialogue. Previous work on event extraction focused on newswire, however we are interested in extracting events from spoken dialogue. To ground this study, we annotated dialogue transcripts from fourteen episodes of the podcast This American Life. This corpus contains 1,038 utterances, made up of 16,962 tokens, of which 3,664 represent events. The agreement for this corpus has a Cohen{'}s Kappa of 0.83. We have open-sourced this corpus for the NLP community. With this corpus in hand, we trained support vector machines (SVM) to correctly classify these phenomena with 0.68 F1, when using episode-fold cross-validation. This is nearly 100{\%} higher F1 than the baseline classifier. The SVM models achieved performance of over 0.75 F1 on some testing folds. We report the results for SVM classifiers trained with four different types of features (verb classes, part of speech tags, named entities, and semantic role labels), and different machine learning protocols (under-sampling and trigram context). This work is grounded in narratology and computational models of narrative. It is useful for extracting events, plot, and story content from spoken dialogue.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eisenberg-sheriff-2020-automatic">
<titleInfo>
<title>Automatic extraction of personal events from dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Eisenberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Sheriff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Joint Workshop on Narrative Understanding, Storylines, and Events</title>
</titleInfo>
<name type="personal">
<namePart type="given">Claire</namePart>
<namePart type="family">Bonial</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommaso</namePart>
<namePart type="family">Caselli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Snigdha</namePart>
<namePart type="family">Chaturvedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Clark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruihong</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Iyyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alejandro</namePart>
<namePart type="family">Jaimes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lara</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Martin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Miller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teruko</namePart>
<namePart type="family">Mitamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we introduce the problem of extracting events from dialogue. Previous work on event extraction focused on newswire, however we are interested in extracting events from spoken dialogue. To ground this study, we annotated dialogue transcripts from fourteen episodes of the podcast This American Life. This corpus contains 1,038 utterances, made up of 16,962 tokens, of which 3,664 represent events. The agreement for this corpus has a Cohen’s Kappa of 0.83. We have open-sourced this corpus for the NLP community. With this corpus in hand, we trained support vector machines (SVM) to correctly classify these phenomena with 0.68 F1, when using episode-fold cross-validation. This is nearly 100% higher F1 than the baseline classifier. The SVM models achieved performance of over 0.75 F1 on some testing folds. We report the results for SVM classifiers trained with four different types of features (verb classes, part of speech tags, named entities, and semantic role labels), and different machine learning protocols (under-sampling and trigram context). This work is grounded in narratology and computational models of narrative. It is useful for extracting events, plot, and story content from spoken dialogue.</abstract>
<identifier type="citekey">eisenberg-sheriff-2020-automatic</identifier>
<identifier type="doi">10.18653/v1/2020.nuse-1.8</identifier>
<location>
<url>https://aclanthology.org/2020.nuse-1.8</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>63</start>
<end>71</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic extraction of personal events from dialogue
%A Eisenberg, Joshua
%A Sheriff, Michael
%Y Bonial, Claire
%Y Caselli, Tommaso
%Y Chaturvedi, Snigdha
%Y Clark, Elizabeth
%Y Huang, Ruihong
%Y Iyyer, Mohit
%Y Jaimes, Alejandro
%Y Ji, Heng
%Y Martin, Lara J.
%Y Miller, Ben
%Y Mitamura, Teruko
%Y Peng, Nanyun
%Y Tetreault, Joel
%S Proceedings of the First Joint Workshop on Narrative Understanding, Storylines, and Events
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F eisenberg-sheriff-2020-automatic
%X In this paper we introduce the problem of extracting events from dialogue. Previous work on event extraction focused on newswire, however we are interested in extracting events from spoken dialogue. To ground this study, we annotated dialogue transcripts from fourteen episodes of the podcast This American Life. This corpus contains 1,038 utterances, made up of 16,962 tokens, of which 3,664 represent events. The agreement for this corpus has a Cohen’s Kappa of 0.83. We have open-sourced this corpus for the NLP community. With this corpus in hand, we trained support vector machines (SVM) to correctly classify these phenomena with 0.68 F1, when using episode-fold cross-validation. This is nearly 100% higher F1 than the baseline classifier. The SVM models achieved performance of over 0.75 F1 on some testing folds. We report the results for SVM classifiers trained with four different types of features (verb classes, part of speech tags, named entities, and semantic role labels), and different machine learning protocols (under-sampling and trigram context). This work is grounded in narratology and computational models of narrative. It is useful for extracting events, plot, and story content from spoken dialogue.
%R 10.18653/v1/2020.nuse-1.8
%U https://aclanthology.org/2020.nuse-1.8
%U https://doi.org/10.18653/v1/2020.nuse-1.8
%P 63-71
Markdown (Informal)
[Automatic extraction of personal events from dialogue](https://aclanthology.org/2020.nuse-1.8) (Eisenberg & Sheriff, NUSE-WNU 2020)
ACL