@inproceedings{dwojak-etal-2020-dataset,
title = "From Dataset Recycling to Multi-Property Extraction and Beyond",
author = "Dwojak, Tomasz and
Pietruszka, Micha{\l} and
Borchmann, {\L}ukasz and
Ch{\l}{\k{e}}dowski, Jakub and
Grali{\'n}ski, Filip",
editor = "Fern{\'a}ndez, Raquel and
Linzen, Tal",
booktitle = "Proceedings of the 24th Conference on Computational Natural Language Learning",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.conll-1.52/",
doi = "10.18653/v1/2020.conll-1.52",
pages = "641--651",
abstract = "This paper investigates various Transformer architectures on the WikiReading Information Extraction and Machine Reading Comprehension dataset. The proposed dual-source model outperforms the current state-of-the-art by a large margin. Next, we introduce WikiReading Recycled - a newly developed public dataset, and the task of multiple-property extraction. It uses the same data as WikiReading but does not inherit its predecessor`s identified disadvantages. In addition, we provide a human-annotated test set with diagnostic subsets for a detailed analysis of model performance."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dwojak-etal-2020-dataset">
<titleInfo>
<title>From Dataset Recycling to Multi-Property Extraction and Beyond</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomasz</namePart>
<namePart type="family">Dwojak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michał</namePart>
<namePart type="family">Pietruszka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Łukasz</namePart>
<namePart type="family">Borchmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakub</namePart>
<namePart type="family">Chłędowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Graliński</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Fernández</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Linzen</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>This paper investigates various Transformer architectures on the WikiReading Information Extraction and Machine Reading Comprehension dataset. The proposed dual-source model outperforms the current state-of-the-art by a large margin. Next, we introduce WikiReading Recycled - a newly developed public dataset, and the task of multiple-property extraction. It uses the same data as WikiReading but does not inherit its predecessor‘s identified disadvantages. In addition, we provide a human-annotated test set with diagnostic subsets for a detailed analysis of model performance.</abstract>
<identifier type="citekey">dwojak-etal-2020-dataset</identifier>
<identifier type="doi">10.18653/v1/2020.conll-1.52</identifier>
<location>
<url>https://aclanthology.org/2020.conll-1.52/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>641</start>
<end>651</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Dataset Recycling to Multi-Property Extraction and Beyond
%A Dwojak, Tomasz
%A Pietruszka, Michał
%A Borchmann, Łukasz
%A Chłędowski, Jakub
%A Graliński, Filip
%Y Fernández, Raquel
%Y Linzen, Tal
%S Proceedings of the 24th Conference on Computational Natural Language Learning
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F dwojak-etal-2020-dataset
%X This paper investigates various Transformer architectures on the WikiReading Information Extraction and Machine Reading Comprehension dataset. The proposed dual-source model outperforms the current state-of-the-art by a large margin. Next, we introduce WikiReading Recycled - a newly developed public dataset, and the task of multiple-property extraction. It uses the same data as WikiReading but does not inherit its predecessor‘s identified disadvantages. In addition, we provide a human-annotated test set with diagnostic subsets for a detailed analysis of model performance.
%R 10.18653/v1/2020.conll-1.52
%U https://aclanthology.org/2020.conll-1.52/
%U https://doi.org/10.18653/v1/2020.conll-1.52
%P 641-651
Markdown (Informal)
[From Dataset Recycling to Multi-Property Extraction and Beyond](https://aclanthology.org/2020.conll-1.52/) (Dwojak et al., CoNLL 2020)
ACL