@inproceedings{shi-etal-2021-descgen,
title = "{DESCGEN}: A Distantly Supervised Datasetfor Generating Entity Descriptions",
author = "Shi, Weijia and
Joshi, Mandar and
Zettlemoyer, Luke",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.35",
doi = "10.18653/v1/2021.acl-long.35",
pages = "415--427",
abstract = "Short textual descriptions of entities provide summaries of their key attributes and have been shown to be useful sources of background knowledge for tasks such as entity linking and question answering. However, generating entity descriptions, especially for new and long-tail entities, can be challenging since relevant information is often scattered across multiple sources with varied content and style. We introduce DESCGEN: given mentions spread over multiple documents, the goal is to generate an entity summary description. DESCGEN consists of 37K entity descriptions from Wikipedia and Fandom, each paired with nine evidence documents on average. The documents were collected using a combination of entity linking and hyperlinks into the entity pages, which together provide high-quality distant supervision. Compared to other multi-document summarization tasks, our task is entity-centric, more abstractive, and covers a wide range of domains. We also propose a two-stage extract-then-generate baseline and show that there exists a large gap (19.9{\%} in ROUGE-L) between state-of-art models and human performance, suggesting that the data will support significant future work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2021-descgen">
<titleInfo>
<title>DESCGEN: A Distantly Supervised Datasetfor Generating Entity Descriptions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weijia</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mandar</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Short textual descriptions of entities provide summaries of their key attributes and have been shown to be useful sources of background knowledge for tasks such as entity linking and question answering. However, generating entity descriptions, especially for new and long-tail entities, can be challenging since relevant information is often scattered across multiple sources with varied content and style. We introduce DESCGEN: given mentions spread over multiple documents, the goal is to generate an entity summary description. DESCGEN consists of 37K entity descriptions from Wikipedia and Fandom, each paired with nine evidence documents on average. The documents were collected using a combination of entity linking and hyperlinks into the entity pages, which together provide high-quality distant supervision. Compared to other multi-document summarization tasks, our task is entity-centric, more abstractive, and covers a wide range of domains. We also propose a two-stage extract-then-generate baseline and show that there exists a large gap (19.9% in ROUGE-L) between state-of-art models and human performance, suggesting that the data will support significant future work.</abstract>
<identifier type="citekey">shi-etal-2021-descgen</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.35</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.35</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>415</start>
<end>427</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DESCGEN: A Distantly Supervised Datasetfor Generating Entity Descriptions
%A Shi, Weijia
%A Joshi, Mandar
%A Zettlemoyer, Luke
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F shi-etal-2021-descgen
%X Short textual descriptions of entities provide summaries of their key attributes and have been shown to be useful sources of background knowledge for tasks such as entity linking and question answering. However, generating entity descriptions, especially for new and long-tail entities, can be challenging since relevant information is often scattered across multiple sources with varied content and style. We introduce DESCGEN: given mentions spread over multiple documents, the goal is to generate an entity summary description. DESCGEN consists of 37K entity descriptions from Wikipedia and Fandom, each paired with nine evidence documents on average. The documents were collected using a combination of entity linking and hyperlinks into the entity pages, which together provide high-quality distant supervision. Compared to other multi-document summarization tasks, our task is entity-centric, more abstractive, and covers a wide range of domains. We also propose a two-stage extract-then-generate baseline and show that there exists a large gap (19.9% in ROUGE-L) between state-of-art models and human performance, suggesting that the data will support significant future work.
%R 10.18653/v1/2021.acl-long.35
%U https://aclanthology.org/2021.acl-long.35
%U https://doi.org/10.18653/v1/2021.acl-long.35
%P 415-427
Markdown (Informal)
[DESCGEN: A Distantly Supervised Datasetfor Generating Entity Descriptions](https://aclanthology.org/2021.acl-long.35) (Shi et al., ACL-IJCNLP 2021)
ACL
- Weijia Shi, Mandar Joshi, and Luke Zettlemoyer. 2021. DESCGEN: A Distantly Supervised Datasetfor Generating Entity Descriptions. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 415–427, Online. Association for Computational Linguistics.