@inproceedings{zemlyanskiy-etal-2021-readtwice,
title = "{R}ead{T}wice: Reading Very Large Documents with Memories",
author = "Zemlyanskiy, Yury and
Ainslie, Joshua and
de Jong, Michiel and
Pham, Philip and
Eckstein, Ilya and
Sha, Fei",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.408",
doi = "10.18653/v1/2021.naacl-main.408",
pages = "5189--5195",
abstract = "Knowledge-intensive tasks such as question answering often require assimilating information from different sections of large inputs such as books or article collections. We propose ReadTwice, a simple and effective technique that combines several strengths of prior approaches to model long-range dependencies with Transformers. The main idea is to read text in small segments, in parallel, summarizing each segment into a memory table to be used in a second read of the text. We show that the method outperforms models of comparable size on several question answering (QA) datasets and sets a new state of the art on the challenging NarrativeQA task, with questions about entire books.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zemlyanskiy-etal-2021-readtwice">
<titleInfo>
<title>ReadTwice: Reading Very Large Documents with Memories</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yury</namePart>
<namePart type="family">Zemlyanskiy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Ainslie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michiel</namePart>
<namePart type="family">de Jong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilya</namePart>
<namePart type="family">Eckstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Sha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Knowledge-intensive tasks such as question answering often require assimilating information from different sections of large inputs such as books or article collections. We propose ReadTwice, a simple and effective technique that combines several strengths of prior approaches to model long-range dependencies with Transformers. The main idea is to read text in small segments, in parallel, summarizing each segment into a memory table to be used in a second read of the text. We show that the method outperforms models of comparable size on several question answering (QA) datasets and sets a new state of the art on the challenging NarrativeQA task, with questions about entire books.</abstract>
<identifier type="citekey">zemlyanskiy-etal-2021-readtwice</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.408</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.408</url>
</location>
<part>
<date>2021-jun</date>
<extent unit="page">
<start>5189</start>
<end>5195</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ReadTwice: Reading Very Large Documents with Memories
%A Zemlyanskiy, Yury
%A Ainslie, Joshua
%A de Jong, Michiel
%A Pham, Philip
%A Eckstein, Ilya
%A Sha, Fei
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 jun
%I Association for Computational Linguistics
%C Online
%F zemlyanskiy-etal-2021-readtwice
%X Knowledge-intensive tasks such as question answering often require assimilating information from different sections of large inputs such as books or article collections. We propose ReadTwice, a simple and effective technique that combines several strengths of prior approaches to model long-range dependencies with Transformers. The main idea is to read text in small segments, in parallel, summarizing each segment into a memory table to be used in a second read of the text. We show that the method outperforms models of comparable size on several question answering (QA) datasets and sets a new state of the art on the challenging NarrativeQA task, with questions about entire books.
%R 10.18653/v1/2021.naacl-main.408
%U https://aclanthology.org/2021.naacl-main.408
%U https://doi.org/10.18653/v1/2021.naacl-main.408
%P 5189-5195
Markdown (Informal)
[ReadTwice: Reading Very Large Documents with Memories](https://aclanthology.org/2021.naacl-main.408) (Zemlyanskiy et al., NAACL 2021)
ACL
- Yury Zemlyanskiy, Joshua Ainslie, Michiel de Jong, Philip Pham, Ilya Eckstein, and Fei Sha. 2021. ReadTwice: Reading Very Large Documents with Memories. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5189–5195, Online. Association for Computational Linguistics.