@inproceedings{rijhwani-preotiuc-pietro-2020-temporally,
title = "Temporally-Informed Analysis of Named Entity Recognition",
author = "Rijhwani, Shruti and
Preotiuc-Pietro, Daniel",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.680",
doi = "10.18653/v1/2020.acl-main.680",
pages = "7605--7617",
abstract = "Natural language processing models often have to make predictions on text data that evolves over time as a result of changes in language use or the information described in the text. However, evaluation results on existing data sets are seldom reported by taking the timestamp of the document into account. We analyze and propose methods that make better use of temporally-diverse training data, with a focus on the task of named entity recognition. To support these experiments, we introduce a novel data set of English tweets annotated with named entities. We empirically demonstrate the effect of temporal drift on performance, and how the temporal information of documents can be used to obtain better models compared to those that disregard temporal information. Our analysis gives insights into why this information is useful, in the hope of informing potential avenues of improvement for named entity recognition as well as other NLP tasks under similar experimental setups.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rijhwani-preotiuc-pietro-2020-temporally">
<titleInfo>
<title>Temporally-Informed Analysis of Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Rijhwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preotiuc-Pietro</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 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</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>Natural language processing models often have to make predictions on text data that evolves over time as a result of changes in language use or the information described in the text. However, evaluation results on existing data sets are seldom reported by taking the timestamp of the document into account. We analyze and propose methods that make better use of temporally-diverse training data, with a focus on the task of named entity recognition. To support these experiments, we introduce a novel data set of English tweets annotated with named entities. We empirically demonstrate the effect of temporal drift on performance, and how the temporal information of documents can be used to obtain better models compared to those that disregard temporal information. Our analysis gives insights into why this information is useful, in the hope of informing potential avenues of improvement for named entity recognition as well as other NLP tasks under similar experimental setups.</abstract>
<identifier type="citekey">rijhwani-preotiuc-pietro-2020-temporally</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.680</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.680</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>7605</start>
<end>7617</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Temporally-Informed Analysis of Named Entity Recognition
%A Rijhwani, Shruti
%A Preotiuc-Pietro, Daniel
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F rijhwani-preotiuc-pietro-2020-temporally
%X Natural language processing models often have to make predictions on text data that evolves over time as a result of changes in language use or the information described in the text. However, evaluation results on existing data sets are seldom reported by taking the timestamp of the document into account. We analyze and propose methods that make better use of temporally-diverse training data, with a focus on the task of named entity recognition. To support these experiments, we introduce a novel data set of English tweets annotated with named entities. We empirically demonstrate the effect of temporal drift on performance, and how the temporal information of documents can be used to obtain better models compared to those that disregard temporal information. Our analysis gives insights into why this information is useful, in the hope of informing potential avenues of improvement for named entity recognition as well as other NLP tasks under similar experimental setups.
%R 10.18653/v1/2020.acl-main.680
%U https://aclanthology.org/2020.acl-main.680
%U https://doi.org/10.18653/v1/2020.acl-main.680
%P 7605-7617
Markdown (Informal)
[Temporally-Informed Analysis of Named Entity Recognition](https://aclanthology.org/2020.acl-main.680) (Rijhwani & Preotiuc-Pietro, ACL 2020)
ACL