@inproceedings{epure-hennequin-2022-probing,
title = "Probing Pre-trained Auto-regressive Language Models for Named Entity Typing and Recognition",
author = "Epure, Elena V. and
Hennequin, Romain",
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-1.151",
pages = "1408--1417",
abstract = "Multiple works have proposed to probe language models (LMs) for generalization in named entity (NE) typing (NET) and recognition (NER). However, little has been done in this direction for auto-regressive models despite their popularity and potential to express a wide variety of NLP tasks in the same unified format. We propose a new methodology to probe auto-regressive LMs for NET and NER generalization, which draws inspiration from human linguistic behavior, by resorting to meta-learning. We study NEs of various types individually by designing a zero-shot transfer strategy for NET. Then, we probe the model for NER by providing a few examples at inference. We introduce a novel procedure to assess the model{'}s memorization of NEs and report the memorization{'}s impact on the results. Our findings show that: 1) GPT2, a common pre-trained auto-regressive LM, without any fine-tuning for NET or NER, performs the tasksfairly well; 2) name irregularity when common for a NE type could be an effective exploitable cue; 3) the model seems to rely more on NE than contextual cues in few-shot NER; 4) NEs with words absent during LM pre-training are very challenging for both NET and NER.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="epure-hennequin-2022-probing">
<titleInfo>
<title>Probing Pre-trained Auto-regressive Language Models for Named Entity Typing and Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Epure</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Romain</namePart>
<namePart type="family">Hennequin</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>Multiple works have proposed to probe language models (LMs) for generalization in named entity (NE) typing (NET) and recognition (NER). However, little has been done in this direction for auto-regressive models despite their popularity and potential to express a wide variety of NLP tasks in the same unified format. We propose a new methodology to probe auto-regressive LMs for NET and NER generalization, which draws inspiration from human linguistic behavior, by resorting to meta-learning. We study NEs of various types individually by designing a zero-shot transfer strategy for NET. Then, we probe the model for NER by providing a few examples at inference. We introduce a novel procedure to assess the model’s memorization of NEs and report the memorization’s impact on the results. Our findings show that: 1) GPT2, a common pre-trained auto-regressive LM, without any fine-tuning for NET or NER, performs the tasksfairly well; 2) name irregularity when common for a NE type could be an effective exploitable cue; 3) the model seems to rely more on NE than contextual cues in few-shot NER; 4) NEs with words absent during LM pre-training are very challenging for both NET and NER.</abstract>
<identifier type="citekey">epure-hennequin-2022-probing</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.151</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>1408</start>
<end>1417</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Probing Pre-trained Auto-regressive Language Models for Named Entity Typing and Recognition
%A Epure, Elena V.
%A Hennequin, Romain
%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 epure-hennequin-2022-probing
%X Multiple works have proposed to probe language models (LMs) for generalization in named entity (NE) typing (NET) and recognition (NER). However, little has been done in this direction for auto-regressive models despite their popularity and potential to express a wide variety of NLP tasks in the same unified format. We propose a new methodology to probe auto-regressive LMs for NET and NER generalization, which draws inspiration from human linguistic behavior, by resorting to meta-learning. We study NEs of various types individually by designing a zero-shot transfer strategy for NET. Then, we probe the model for NER by providing a few examples at inference. We introduce a novel procedure to assess the model’s memorization of NEs and report the memorization’s impact on the results. Our findings show that: 1) GPT2, a common pre-trained auto-regressive LM, without any fine-tuning for NET or NER, performs the tasksfairly well; 2) name irregularity when common for a NE type could be an effective exploitable cue; 3) the model seems to rely more on NE than contextual cues in few-shot NER; 4) NEs with words absent during LM pre-training are very challenging for both NET and NER.
%U https://aclanthology.org/2022.lrec-1.151
%P 1408-1417
Markdown (Informal)
[Probing Pre-trained Auto-regressive Language Models for Named Entity Typing and Recognition](https://aclanthology.org/2022.lrec-1.151) (Epure & Hennequin, LREC 2022)
ACL