@inproceedings{arora-etal-2021-identifying,
title = "Identifying Named Entities as they are Typed",
author = "Arora, Ravneet and
Tsai, Chen-Tse and
Preotiuc-Pietro, Daniel",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.84",
doi = "10.18653/v1/2021.eacl-main.84",
pages = "976--988",
abstract = "Identifying named entities in written text is an essential component of the text processing pipeline used in applications such as text editors to gain a better understanding of the semantics of the text. However, the typical experimental setup for evaluating Named Entity Recognition (NER) systems is not directly applicable to systems that process text in real time as the text is being typed. Evaluation is performed on a sentence level assuming the end-user is willing to wait until the entire sentence is typed for entities to be identified and further linked to identifiers or co-referenced. We introduce a novel experimental setup for NER systems for applications where decisions about named entity boundaries need to be performed in an online fashion. We study how state-of-the-art methods perform under this setup in multiple languages and propose adaptations to these models to suit this new experimental setup. Experimental results show that the best systems that are evaluated on each token after its typed, reach performance within 1{--}5 F1 points of systems that are evaluated at the end of the sentence. These show that entity recognition can be performed in this setup and open up the development of other NLP tools in a similar setup.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arora-etal-2021-identifying">
<titleInfo>
<title>Identifying Named Entities as they are Typed</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ravneet</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen-Tse</namePart>
<namePart type="family">Tsai</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>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</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>Identifying named entities in written text is an essential component of the text processing pipeline used in applications such as text editors to gain a better understanding of the semantics of the text. However, the typical experimental setup for evaluating Named Entity Recognition (NER) systems is not directly applicable to systems that process text in real time as the text is being typed. Evaluation is performed on a sentence level assuming the end-user is willing to wait until the entire sentence is typed for entities to be identified and further linked to identifiers or co-referenced. We introduce a novel experimental setup for NER systems for applications where decisions about named entity boundaries need to be performed in an online fashion. We study how state-of-the-art methods perform under this setup in multiple languages and propose adaptations to these models to suit this new experimental setup. Experimental results show that the best systems that are evaluated on each token after its typed, reach performance within 1–5 F1 points of systems that are evaluated at the end of the sentence. These show that entity recognition can be performed in this setup and open up the development of other NLP tools in a similar setup.</abstract>
<identifier type="citekey">arora-etal-2021-identifying</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.84</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.84</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>976</start>
<end>988</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Identifying Named Entities as they are Typed
%A Arora, Ravneet
%A Tsai, Chen-Tse
%A Preotiuc-Pietro, Daniel
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F arora-etal-2021-identifying
%X Identifying named entities in written text is an essential component of the text processing pipeline used in applications such as text editors to gain a better understanding of the semantics of the text. However, the typical experimental setup for evaluating Named Entity Recognition (NER) systems is not directly applicable to systems that process text in real time as the text is being typed. Evaluation is performed on a sentence level assuming the end-user is willing to wait until the entire sentence is typed for entities to be identified and further linked to identifiers or co-referenced. We introduce a novel experimental setup for NER systems for applications where decisions about named entity boundaries need to be performed in an online fashion. We study how state-of-the-art methods perform under this setup in multiple languages and propose adaptations to these models to suit this new experimental setup. Experimental results show that the best systems that are evaluated on each token after its typed, reach performance within 1–5 F1 points of systems that are evaluated at the end of the sentence. These show that entity recognition can be performed in this setup and open up the development of other NLP tools in a similar setup.
%R 10.18653/v1/2021.eacl-main.84
%U https://aclanthology.org/2021.eacl-main.84
%U https://doi.org/10.18653/v1/2021.eacl-main.84
%P 976-988
Markdown (Informal)
[Identifying Named Entities as they are Typed](https://aclanthology.org/2021.eacl-main.84) (Arora et al., EACL 2021)
ACL
- Ravneet Arora, Chen-Tse Tsai, and Daniel Preotiuc-Pietro. 2021. Identifying Named Entities as they are Typed. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 976–988, Online. Association for Computational Linguistics.