@inproceedings{mahapatra-etal-2022-entity,
title = "Entity Extraction in Low Resource Domains with Selective Pre-training of Large Language Models",
author = "Mahapatra, Aniruddha and
Nangi, Sharmila Reddy and
Garimella, Aparna and
N, Anandhavelu",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.61",
doi = "10.18653/v1/2022.emnlp-main.61",
pages = "942--951",
abstract = "Transformer-based language models trained on large natural language corpora have been very useful in downstream entity extraction tasks. However, they often result in poor performances when applied to domains that are different from those they are pretrained on. Continued pretraining using unlabeled data from target domains can help improve the performances of these language models on the downstream tasks. However, using all of the available unlabeled data for pretraining can be time-intensive; also, it can be detrimental to the performance of the downstream tasks, if the unlabeled data is not aligned with the data distribution for the target tasks. Previous works employed external supervision in the form of ontologies for selecting appropriate data samples for pretraining, but external supervision can be quite hard to obtain in low-resource domains. In this paper, we introduce effective ways to select data from unlabeled corpora of target domains for language model pretraining to improve the performances in target entity extraction tasks. Our data selection strategies do not require any external supervision. We conduct extensive experiments for the task of named entity recognition (NER) on seven different domains and show that language models pretrained on target domain unlabeled data obtained using our data selection strategies achieve better performances compared to those using data selection strategies in previous works that use external supervision. We also show that these pretrained language models using our data selection strategies outperform those pretrained on all of the available unlabeled target domain data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mahapatra-etal-2022-entity">
<titleInfo>
<title>Entity Extraction in Low Resource Domains with Selective Pre-training of Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aniruddha</namePart>
<namePart type="family">Mahapatra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sharmila</namePart>
<namePart type="given">Reddy</namePart>
<namePart type="family">Nangi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aparna</namePart>
<namePart type="family">Garimella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anandhavelu</namePart>
<namePart type="family">N</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Transformer-based language models trained on large natural language corpora have been very useful in downstream entity extraction tasks. However, they often result in poor performances when applied to domains that are different from those they are pretrained on. Continued pretraining using unlabeled data from target domains can help improve the performances of these language models on the downstream tasks. However, using all of the available unlabeled data for pretraining can be time-intensive; also, it can be detrimental to the performance of the downstream tasks, if the unlabeled data is not aligned with the data distribution for the target tasks. Previous works employed external supervision in the form of ontologies for selecting appropriate data samples for pretraining, but external supervision can be quite hard to obtain in low-resource domains. In this paper, we introduce effective ways to select data from unlabeled corpora of target domains for language model pretraining to improve the performances in target entity extraction tasks. Our data selection strategies do not require any external supervision. We conduct extensive experiments for the task of named entity recognition (NER) on seven different domains and show that language models pretrained on target domain unlabeled data obtained using our data selection strategies achieve better performances compared to those using data selection strategies in previous works that use external supervision. We also show that these pretrained language models using our data selection strategies outperform those pretrained on all of the available unlabeled target domain data.</abstract>
<identifier type="citekey">mahapatra-etal-2022-entity</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.61</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.61</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>942</start>
<end>951</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Entity Extraction in Low Resource Domains with Selective Pre-training of Large Language Models
%A Mahapatra, Aniruddha
%A Nangi, Sharmila Reddy
%A Garimella, Aparna
%A N, Anandhavelu
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F mahapatra-etal-2022-entity
%X Transformer-based language models trained on large natural language corpora have been very useful in downstream entity extraction tasks. However, they often result in poor performances when applied to domains that are different from those they are pretrained on. Continued pretraining using unlabeled data from target domains can help improve the performances of these language models on the downstream tasks. However, using all of the available unlabeled data for pretraining can be time-intensive; also, it can be detrimental to the performance of the downstream tasks, if the unlabeled data is not aligned with the data distribution for the target tasks. Previous works employed external supervision in the form of ontologies for selecting appropriate data samples for pretraining, but external supervision can be quite hard to obtain in low-resource domains. In this paper, we introduce effective ways to select data from unlabeled corpora of target domains for language model pretraining to improve the performances in target entity extraction tasks. Our data selection strategies do not require any external supervision. We conduct extensive experiments for the task of named entity recognition (NER) on seven different domains and show that language models pretrained on target domain unlabeled data obtained using our data selection strategies achieve better performances compared to those using data selection strategies in previous works that use external supervision. We also show that these pretrained language models using our data selection strategies outperform those pretrained on all of the available unlabeled target domain data.
%R 10.18653/v1/2022.emnlp-main.61
%U https://aclanthology.org/2022.emnlp-main.61
%U https://doi.org/10.18653/v1/2022.emnlp-main.61
%P 942-951
Markdown (Informal)
[Entity Extraction in Low Resource Domains with Selective Pre-training of Large Language Models](https://aclanthology.org/2022.emnlp-main.61) (Mahapatra et al., EMNLP 2022)
ACL