@inproceedings{loaiciga-etal-2022-new,
title = "New or Old? Exploring How Pre-Trained Language Models Represent Discourse Entities",
author = "Lo{\'a}iciga, Sharid and
Beyer, Anne and
Schlangen, David",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.73",
pages = "875--886",
abstract = "Recent research shows that pre-trained language models, built to generate text conditioned on some context, learn to encode syntactic knowledge to a certain degree. This has motivated researchers to move beyond the sentence-level and look into their ability to encode less studied discourse-level phenomena. In this paper, we add to the body of probing research by investigating discourse entity representations in large pre-trained language models in English. Motivated by early theories of discourse and key pieces of previous work, we focus on the information-status of entities as discourse-new or discourse-old. We present two probing models, one based on binary classification and another one on sequence labeling. The results of our experiments show that pre-trained language models do encode information on whether an entity has been introduced before or not in the discourse. However, this information alone is not sufficient to find the entities in a discourse, opening up interesting questions about the definition of entities for future work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="loaiciga-etal-2022-new">
<titleInfo>
<title>New or Old? Exploring How Pre-Trained Language Models Represent Discourse Entities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sharid</namePart>
<namePart type="family">Loáiciga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Beyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Schlangen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</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">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent research shows that pre-trained language models, built to generate text conditioned on some context, learn to encode syntactic knowledge to a certain degree. This has motivated researchers to move beyond the sentence-level and look into their ability to encode less studied discourse-level phenomena. In this paper, we add to the body of probing research by investigating discourse entity representations in large pre-trained language models in English. Motivated by early theories of discourse and key pieces of previous work, we focus on the information-status of entities as discourse-new or discourse-old. We present two probing models, one based on binary classification and another one on sequence labeling. The results of our experiments show that pre-trained language models do encode information on whether an entity has been introduced before or not in the discourse. However, this information alone is not sufficient to find the entities in a discourse, opening up interesting questions about the definition of entities for future work.</abstract>
<identifier type="citekey">loaiciga-etal-2022-new</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.73</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>875</start>
<end>886</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T New or Old? Exploring How Pre-Trained Language Models Represent Discourse Entities
%A Loáiciga, Sharid
%A Beyer, Anne
%A Schlangen, David
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F loaiciga-etal-2022-new
%X Recent research shows that pre-trained language models, built to generate text conditioned on some context, learn to encode syntactic knowledge to a certain degree. This has motivated researchers to move beyond the sentence-level and look into their ability to encode less studied discourse-level phenomena. In this paper, we add to the body of probing research by investigating discourse entity representations in large pre-trained language models in English. Motivated by early theories of discourse and key pieces of previous work, we focus on the information-status of entities as discourse-new or discourse-old. We present two probing models, one based on binary classification and another one on sequence labeling. The results of our experiments show that pre-trained language models do encode information on whether an entity has been introduced before or not in the discourse. However, this information alone is not sufficient to find the entities in a discourse, opening up interesting questions about the definition of entities for future work.
%U https://aclanthology.org/2022.coling-1.73
%P 875-886
Markdown (Informal)
[New or Old? Exploring How Pre-Trained Language Models Represent Discourse Entities](https://aclanthology.org/2022.coling-1.73) (Loáiciga et al., COLING 2022)
ACL