@inproceedings{sui-etal-2021-set,
title = "Set Generation Networks for End-to-End Knowledge Base Population",
author = "Sui, Dianbo and
Wang, Chenhao and
Chen, Yubo and
Liu, Kang and
Zhao, Jun and
Bi, Wei",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.760",
doi = "10.18653/v1/2021.emnlp-main.760",
pages = "9650--9660",
abstract = "The task of knowledge base population (KBP) aims to discover facts about entities from texts and expand a knowledge base with these facts. Previous studies shape end-to-end KBP as a machine translation task, which is required to convert unordered fact into a sequence according to a pre-specified order. However, the facts stated in a sentence are unordered in essence. In this paper, we formulate end-to-end KBP as a direct set generation problem, avoiding considering the order of multiple facts. To solve the set generation problem, we propose networks featured by transformers with non-autoregressive parallel decoding. Unlike previous approaches that use an autoregressive decoder to generate facts one by one, the proposed networks can directly output the final set of facts in one shot. Furthermore, to train the networks, we also design a set-based loss that forces unique predictions via bipartite matching. Compared with cross-entropy loss that highly penalizes small shifts in fact order, the proposed bipartite matching loss is invariant to any permutation of predictions. Benefiting from getting rid of the burden of predicting the order of multiple facts, our proposed networks achieve state-of-the-art (SoTA) performance on two benchmark datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sui-etal-2021-set">
<titleInfo>
<title>Set Generation Networks for End-to-End Knowledge Base Population</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dianbo</namePart>
<namePart type="family">Sui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenhao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Bi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The task of knowledge base population (KBP) aims to discover facts about entities from texts and expand a knowledge base with these facts. Previous studies shape end-to-end KBP as a machine translation task, which is required to convert unordered fact into a sequence according to a pre-specified order. However, the facts stated in a sentence are unordered in essence. In this paper, we formulate end-to-end KBP as a direct set generation problem, avoiding considering the order of multiple facts. To solve the set generation problem, we propose networks featured by transformers with non-autoregressive parallel decoding. Unlike previous approaches that use an autoregressive decoder to generate facts one by one, the proposed networks can directly output the final set of facts in one shot. Furthermore, to train the networks, we also design a set-based loss that forces unique predictions via bipartite matching. Compared with cross-entropy loss that highly penalizes small shifts in fact order, the proposed bipartite matching loss is invariant to any permutation of predictions. Benefiting from getting rid of the burden of predicting the order of multiple facts, our proposed networks achieve state-of-the-art (SoTA) performance on two benchmark datasets.</abstract>
<identifier type="citekey">sui-etal-2021-set</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.760</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.760</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>9650</start>
<end>9660</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Set Generation Networks for End-to-End Knowledge Base Population
%A Sui, Dianbo
%A Wang, Chenhao
%A Chen, Yubo
%A Liu, Kang
%A Zhao, Jun
%A Bi, Wei
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F sui-etal-2021-set
%X The task of knowledge base population (KBP) aims to discover facts about entities from texts and expand a knowledge base with these facts. Previous studies shape end-to-end KBP as a machine translation task, which is required to convert unordered fact into a sequence according to a pre-specified order. However, the facts stated in a sentence are unordered in essence. In this paper, we formulate end-to-end KBP as a direct set generation problem, avoiding considering the order of multiple facts. To solve the set generation problem, we propose networks featured by transformers with non-autoregressive parallel decoding. Unlike previous approaches that use an autoregressive decoder to generate facts one by one, the proposed networks can directly output the final set of facts in one shot. Furthermore, to train the networks, we also design a set-based loss that forces unique predictions via bipartite matching. Compared with cross-entropy loss that highly penalizes small shifts in fact order, the proposed bipartite matching loss is invariant to any permutation of predictions. Benefiting from getting rid of the burden of predicting the order of multiple facts, our proposed networks achieve state-of-the-art (SoTA) performance on two benchmark datasets.
%R 10.18653/v1/2021.emnlp-main.760
%U https://aclanthology.org/2021.emnlp-main.760
%U https://doi.org/10.18653/v1/2021.emnlp-main.760
%P 9650-9660
Markdown (Informal)
[Set Generation Networks for End-to-End Knowledge Base Population](https://aclanthology.org/2021.emnlp-main.760) (Sui et al., EMNLP 2021)
ACL
- Dianbo Sui, Chenhao Wang, Yubo Chen, Kang Liu, Jun Zhao, and Wei Bi. 2021. Set Generation Networks for End-to-End Knowledge Base Population. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9650–9660, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.