@inproceedings{vajjala-balasubramaniam-2022-really,
title = "What do we really know about State of the Art {NER}?",
author = "Vajjala, Sowmya and
Balasubramaniam, Ramya",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.643",
pages = "5983--5993",
abstract = "Named Entity Recognition (NER) is a well researched NLP task and is widely used in real world NLP scenarios. NER research typically focuses on the creation of new ways of training NER, with relatively less emphasis on resources and evaluation. Further, state of the art (SOTA) NER models, trained on standard datasets, typically report only a single performance measure (F-score) and we don{'}t really know how well they do for different entity types and genres of text, or how robust are they to new, unseen entities. In this paper, we perform a broad evaluation of NER using a popular dataset, that takes into consideration various text genres and sources constituting the dataset at hand. Additionally, we generate six new adversarial test sets through small perturbations in the original test set, replacing select entities while retaining the context. We also train and test our models on randomly generated train/dev/test splits followed by an experiment where the models are trained on a select set of genres but tested genres not seen in training. These comprehensive evaluation strategies were performed using three SOTA NER models. Based on our results, we recommend some useful reporting practices for NER researchers, that could help in providing a better understanding of a SOTA model{'}s performance in future.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vajjala-balasubramaniam-2022-really">
<titleInfo>
<title>What do we really know about State of the Art NER?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sowmya</namePart>
<namePart type="family">Vajjala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramya</namePart>
<namePart type="family">Balasubramaniam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Named Entity Recognition (NER) is a well researched NLP task and is widely used in real world NLP scenarios. NER research typically focuses on the creation of new ways of training NER, with relatively less emphasis on resources and evaluation. Further, state of the art (SOTA) NER models, trained on standard datasets, typically report only a single performance measure (F-score) and we don’t really know how well they do for different entity types and genres of text, or how robust are they to new, unseen entities. In this paper, we perform a broad evaluation of NER using a popular dataset, that takes into consideration various text genres and sources constituting the dataset at hand. Additionally, we generate six new adversarial test sets through small perturbations in the original test set, replacing select entities while retaining the context. We also train and test our models on randomly generated train/dev/test splits followed by an experiment where the models are trained on a select set of genres but tested genres not seen in training. These comprehensive evaluation strategies were performed using three SOTA NER models. Based on our results, we recommend some useful reporting practices for NER researchers, that could help in providing a better understanding of a SOTA model’s performance in future.</abstract>
<identifier type="citekey">vajjala-balasubramaniam-2022-really</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.643</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5983</start>
<end>5993</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What do we really know about State of the Art NER?
%A Vajjala, Sowmya
%A Balasubramaniam, Ramya
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F vajjala-balasubramaniam-2022-really
%X Named Entity Recognition (NER) is a well researched NLP task and is widely used in real world NLP scenarios. NER research typically focuses on the creation of new ways of training NER, with relatively less emphasis on resources and evaluation. Further, state of the art (SOTA) NER models, trained on standard datasets, typically report only a single performance measure (F-score) and we don’t really know how well they do for different entity types and genres of text, or how robust are they to new, unseen entities. In this paper, we perform a broad evaluation of NER using a popular dataset, that takes into consideration various text genres and sources constituting the dataset at hand. Additionally, we generate six new adversarial test sets through small perturbations in the original test set, replacing select entities while retaining the context. We also train and test our models on randomly generated train/dev/test splits followed by an experiment where the models are trained on a select set of genres but tested genres not seen in training. These comprehensive evaluation strategies were performed using three SOTA NER models. Based on our results, we recommend some useful reporting practices for NER researchers, that could help in providing a better understanding of a SOTA model’s performance in future.
%U https://aclanthology.org/2022.lrec-1.643
%P 5983-5993
Markdown (Informal)
[What do we really know about State of the Art NER?](https://aclanthology.org/2022.lrec-1.643) (Vajjala & Balasubramaniam, LREC 2022)
ACL
- Sowmya Vajjala and Ramya Balasubramaniam. 2022. What do we really know about State of the Art NER?. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 5983–5993, Marseille, France. European Language Resources Association.