@inproceedings{drozdov-etal-2020-unsupervised,
title = "Unsupervised Parsing with {S}-{DIORA}: Single Tree Encoding for Deep Inside-Outside Recursive Autoencoders",
author = "Drozdov, Andrew and
Rongali, Subendhu and
Chen, Yi-Pei and
O{'}Gorman, Tim and
Iyyer, Mohit and
McCallum, Andrew",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.392/",
doi = "10.18653/v1/2020.emnlp-main.392",
pages = "4832--4845",
abstract = "The deep inside-outside recursive autoencoder (DIORA; Drozdov et al. 2019) is a self-supervised neural model that learns to induce syntactic tree structures for input sentences *without access to labeled training data*. In this paper, we discover that while DIORA exhaustively encodes all possible binary trees of a sentence with a soft dynamic program, its vector averaging approach is locally greedy and cannot recover from errors when computing the highest scoring parse tree in bottom-up chart parsing. To fix this issue, we introduce S-DIORA, an improved variant of DIORA that encodes a single tree rather than a softly-weighted mixture of trees by employing a hard argmax operation and a beam at each cell in the chart. Our experiments show that through *fine-tuning* a pre-trained DIORA with our new algorithm, we improve the state of the art in *unsupervised* constituency parsing on the English WSJ Penn Treebank by 2.2-6{\%} F1, depending on the data used for fine-tuning."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="drozdov-etal-2020-unsupervised">
<titleInfo>
<title>Unsupervised Parsing with S-DIORA: Single Tree Encoding for Deep Inside-Outside Recursive Autoencoders</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Drozdov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subendhu</namePart>
<namePart type="family">Rongali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi-Pei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">O’Gorman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Iyyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">McCallum</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 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>The deep inside-outside recursive autoencoder (DIORA; Drozdov et al. 2019) is a self-supervised neural model that learns to induce syntactic tree structures for input sentences *without access to labeled training data*. In this paper, we discover that while DIORA exhaustively encodes all possible binary trees of a sentence with a soft dynamic program, its vector averaging approach is locally greedy and cannot recover from errors when computing the highest scoring parse tree in bottom-up chart parsing. To fix this issue, we introduce S-DIORA, an improved variant of DIORA that encodes a single tree rather than a softly-weighted mixture of trees by employing a hard argmax operation and a beam at each cell in the chart. Our experiments show that through *fine-tuning* a pre-trained DIORA with our new algorithm, we improve the state of the art in *unsupervised* constituency parsing on the English WSJ Penn Treebank by 2.2-6% F1, depending on the data used for fine-tuning.</abstract>
<identifier type="citekey">drozdov-etal-2020-unsupervised</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.392</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.392/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>4832</start>
<end>4845</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Parsing with S-DIORA: Single Tree Encoding for Deep Inside-Outside Recursive Autoencoders
%A Drozdov, Andrew
%A Rongali, Subendhu
%A Chen, Yi-Pei
%A O’Gorman, Tim
%A Iyyer, Mohit
%A McCallum, Andrew
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F drozdov-etal-2020-unsupervised
%X The deep inside-outside recursive autoencoder (DIORA; Drozdov et al. 2019) is a self-supervised neural model that learns to induce syntactic tree structures for input sentences *without access to labeled training data*. In this paper, we discover that while DIORA exhaustively encodes all possible binary trees of a sentence with a soft dynamic program, its vector averaging approach is locally greedy and cannot recover from errors when computing the highest scoring parse tree in bottom-up chart parsing. To fix this issue, we introduce S-DIORA, an improved variant of DIORA that encodes a single tree rather than a softly-weighted mixture of trees by employing a hard argmax operation and a beam at each cell in the chart. Our experiments show that through *fine-tuning* a pre-trained DIORA with our new algorithm, we improve the state of the art in *unsupervised* constituency parsing on the English WSJ Penn Treebank by 2.2-6% F1, depending on the data used for fine-tuning.
%R 10.18653/v1/2020.emnlp-main.392
%U https://aclanthology.org/2020.emnlp-main.392/
%U https://doi.org/10.18653/v1/2020.emnlp-main.392
%P 4832-4845
Markdown (Informal)
[Unsupervised Parsing with S-DIORA: Single Tree Encoding for Deep Inside-Outside Recursive Autoencoders](https://aclanthology.org/2020.emnlp-main.392/) (Drozdov et al., EMNLP 2020)
ACL