@inproceedings{arnold-etal-2022-knowledge,
title = "Knowledge extraction from aeronautical messages ({NOTAM}s) with self-supervised language models for aircraft pilots",
author = "Arnold, Alexandre and
Ernez, Fares and
Kobus, Catherine and
Martin, Marion-C{\'e}cile",
editor = "Loukina, Anastassia and
Gangadharaiah, Rashmi and
Min, Bonan",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track",
month = jul,
year = "2022",
address = "Hybrid: Seattle, Washington + Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-industry.22",
doi = "10.18653/v1/2022.naacl-industry.22",
pages = "188--196",
abstract = "During their pre-flight briefings, aircraft pilots must analyse a long list of NoTAMs (NOtice To AirMen) indicating potential hazards along the flight route, sometimes up to pages for long-haul flights. NOTAM free-text fields typically have a very special phrasing, with lots of acronyms and domain-specific vocabulary, which makes it differ significantly from standard English. In this paper, we pretrain language models derived from BERT on circa 1 million unlabeled NOTAMs and reuse the learnt representations on three downstream tasks valuable for pilots: criticality prediction, named entity recognition and translation into a structured language called Airlang. This self-supervised approach, where smaller amounts of labeled data are enough for task-specific fine-tuning, is well suited in the aeronautical context since expert annotations are expensive and time-consuming. We present evaluation scores across the tasks showing a high potential for an operational usability of such models (by pilots, airlines or service providers), which is a first to the best of our knowledge.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arnold-etal-2022-knowledge">
<titleInfo>
<title>Knowledge extraction from aeronautical messages (NOTAMs) with self-supervised language models for aircraft pilots</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandre</namePart>
<namePart type="family">Arnold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fares</namePart>
<namePart type="family">Ernez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Kobus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marion-Cécile</namePart>
<namePart type="family">Martin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anastassia</namePart>
<namePart type="family">Loukina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rashmi</namePart>
<namePart type="family">Gangadharaiah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bonan</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid: Seattle, Washington + Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>During their pre-flight briefings, aircraft pilots must analyse a long list of NoTAMs (NOtice To AirMen) indicating potential hazards along the flight route, sometimes up to pages for long-haul flights. NOTAM free-text fields typically have a very special phrasing, with lots of acronyms and domain-specific vocabulary, which makes it differ significantly from standard English. In this paper, we pretrain language models derived from BERT on circa 1 million unlabeled NOTAMs and reuse the learnt representations on three downstream tasks valuable for pilots: criticality prediction, named entity recognition and translation into a structured language called Airlang. This self-supervised approach, where smaller amounts of labeled data are enough for task-specific fine-tuning, is well suited in the aeronautical context since expert annotations are expensive and time-consuming. We present evaluation scores across the tasks showing a high potential for an operational usability of such models (by pilots, airlines or service providers), which is a first to the best of our knowledge.</abstract>
<identifier type="citekey">arnold-etal-2022-knowledge</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-industry.22</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-industry.22</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>188</start>
<end>196</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowledge extraction from aeronautical messages (NOTAMs) with self-supervised language models for aircraft pilots
%A Arnold, Alexandre
%A Ernez, Fares
%A Kobus, Catherine
%A Martin, Marion-Cécile
%Y Loukina, Anastassia
%Y Gangadharaiah, Rashmi
%Y Min, Bonan
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track
%D 2022
%8 July
%I Association for Computational Linguistics
%C Hybrid: Seattle, Washington + Online
%F arnold-etal-2022-knowledge
%X During their pre-flight briefings, aircraft pilots must analyse a long list of NoTAMs (NOtice To AirMen) indicating potential hazards along the flight route, sometimes up to pages for long-haul flights. NOTAM free-text fields typically have a very special phrasing, with lots of acronyms and domain-specific vocabulary, which makes it differ significantly from standard English. In this paper, we pretrain language models derived from BERT on circa 1 million unlabeled NOTAMs and reuse the learnt representations on three downstream tasks valuable for pilots: criticality prediction, named entity recognition and translation into a structured language called Airlang. This self-supervised approach, where smaller amounts of labeled data are enough for task-specific fine-tuning, is well suited in the aeronautical context since expert annotations are expensive and time-consuming. We present evaluation scores across the tasks showing a high potential for an operational usability of such models (by pilots, airlines or service providers), which is a first to the best of our knowledge.
%R 10.18653/v1/2022.naacl-industry.22
%U https://aclanthology.org/2022.naacl-industry.22
%U https://doi.org/10.18653/v1/2022.naacl-industry.22
%P 188-196
Markdown (Informal)
[Knowledge extraction from aeronautical messages (NOTAMs) with self-supervised language models for aircraft pilots](https://aclanthology.org/2022.naacl-industry.22) (Arnold et al., NAACL 2022)
ACL