@inproceedings{lasri-etal-2023-econberta,
title = "{E}con{BERT}a: Towards Robust Extraction of Named Entities in Economics",
author = "Lasri, Karim and
de Castro, Pedro Vitor Quinta and
Schirmer, Mona and
San Martin, Luis Eduardo and
Wang, Linxi and
Dulka, Tom{\'a}{\v{s}} and
Naushan, Haaya and
Pougu{\'e}-Biyong, John and
Legovini, Arianna and
Fraiberger, Samuel",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.774/",
doi = "10.18653/v1/2023.findings-emnlp.774",
pages = "11557--11577",
abstract = "Adapting general-purpose language models has proven to be effective in tackling downstream tasks within specific domains. In this paper, we address the task of extracting entities from the economics literature on impact evaluation. To this end, we release EconBERTa, a large language model pretrained on scientific publications in economics, and ECON-IE, a new expert-annotated dataset of economics abstracts for Named Entity Recognition (NER). We find that EconBERTa reaches state-of-the-art performance on our downstream NER task. Additionally, we extensively analyze the model`s generalization capacities, finding that most errors correspond to detecting only a subspan of an entity or failure to extrapolate to longer sequences. This limitation is primarily due to an inability to detect part-of-speech sequences unseen during training, and this effect diminishes when the number of unique instances in the training set increases. Examining the generalization abilities of domain-specific language models paves the way towards improving the robustness of NER models for causal knowledge extraction."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lasri-etal-2023-econberta">
<titleInfo>
<title>EconBERTa: Towards Robust Extraction of Named Entities in Economics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karim</namePart>
<namePart type="family">Lasri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="given">Vitor</namePart>
<namePart type="given">Quinta</namePart>
<namePart type="family">de Castro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Schirmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="given">Eduardo</namePart>
<namePart type="family">San Martin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linxi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomáš</namePart>
<namePart type="family">Dulka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haaya</namePart>
<namePart type="family">Naushan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Pougué-Biyong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Legovini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Fraiberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Adapting general-purpose language models has proven to be effective in tackling downstream tasks within specific domains. In this paper, we address the task of extracting entities from the economics literature on impact evaluation. To this end, we release EconBERTa, a large language model pretrained on scientific publications in economics, and ECON-IE, a new expert-annotated dataset of economics abstracts for Named Entity Recognition (NER). We find that EconBERTa reaches state-of-the-art performance on our downstream NER task. Additionally, we extensively analyze the model‘s generalization capacities, finding that most errors correspond to detecting only a subspan of an entity or failure to extrapolate to longer sequences. This limitation is primarily due to an inability to detect part-of-speech sequences unseen during training, and this effect diminishes when the number of unique instances in the training set increases. Examining the generalization abilities of domain-specific language models paves the way towards improving the robustness of NER models for causal knowledge extraction.</abstract>
<identifier type="citekey">lasri-etal-2023-econberta</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.774</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.774/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>11557</start>
<end>11577</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EconBERTa: Towards Robust Extraction of Named Entities in Economics
%A Lasri, Karim
%A de Castro, Pedro Vitor Quinta
%A Schirmer, Mona
%A San Martin, Luis Eduardo
%A Wang, Linxi
%A Dulka, Tomáš
%A Naushan, Haaya
%A Pougué-Biyong, John
%A Legovini, Arianna
%A Fraiberger, Samuel
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F lasri-etal-2023-econberta
%X Adapting general-purpose language models has proven to be effective in tackling downstream tasks within specific domains. In this paper, we address the task of extracting entities from the economics literature on impact evaluation. To this end, we release EconBERTa, a large language model pretrained on scientific publications in economics, and ECON-IE, a new expert-annotated dataset of economics abstracts for Named Entity Recognition (NER). We find that EconBERTa reaches state-of-the-art performance on our downstream NER task. Additionally, we extensively analyze the model‘s generalization capacities, finding that most errors correspond to detecting only a subspan of an entity or failure to extrapolate to longer sequences. This limitation is primarily due to an inability to detect part-of-speech sequences unseen during training, and this effect diminishes when the number of unique instances in the training set increases. Examining the generalization abilities of domain-specific language models paves the way towards improving the robustness of NER models for causal knowledge extraction.
%R 10.18653/v1/2023.findings-emnlp.774
%U https://aclanthology.org/2023.findings-emnlp.774/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.774
%P 11557-11577
Markdown (Informal)
[EconBERTa: Towards Robust Extraction of Named Entities in Economics](https://aclanthology.org/2023.findings-emnlp.774/) (Lasri et al., Findings 2023)
ACL
- Karim Lasri, Pedro Vitor Quinta de Castro, Mona Schirmer, Luis Eduardo San Martin, Linxi Wang, Tomáš Dulka, Haaya Naushan, John Pougué-Biyong, Arianna Legovini, and Samuel Fraiberger. 2023. EconBERTa: Towards Robust Extraction of Named Entities in Economics. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 11557–11577, Singapore. Association for Computational Linguistics.