@inproceedings{tan-etal-2020-recursive,
title = "Recursive Top-Down Production for Sentence Generation with Latent Trees",
author = "Tan, Shawn and
Shen, Yikang and
Sordoni, Alessandro and
Courville, Aaron and
O{'}Donnell, Timothy J.",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.208",
doi = "10.18653/v1/2020.findings-emnlp.208",
pages = "2291--2307",
abstract = "We model the recursive production property of context-free grammars for natural and synthetic languages. To this end, we present a dynamic programming algorithm that marginalises over latent binary tree structures with N leaves, allowing us to compute the likelihood of a sequence of N tokens under a latent tree model, which we maximise to train a recursive neural function. We demonstrate performance on two synthetic tasks: SCAN, where it outperforms previous models on the LENGTH split, and English question formation, where it performs comparably to decoders with the ground-truth tree structure. We also present experimental results on German-English translation on the Multi30k dataset, and qualitatively analyse the induced tree structures our model learns for the SCAN tasks and the German-English translation task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tan-etal-2020-recursive">
<titleInfo>
<title>Recursive Top-Down Production for Sentence Generation with Latent Trees</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shawn</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yikang</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Sordoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Courville</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="given">J</namePart>
<namePart type="family">O’Donnell</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>Findings of the Association for Computational Linguistics: EMNLP 2020</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>We model the recursive production property of context-free grammars for natural and synthetic languages. To this end, we present a dynamic programming algorithm that marginalises over latent binary tree structures with N leaves, allowing us to compute the likelihood of a sequence of N tokens under a latent tree model, which we maximise to train a recursive neural function. We demonstrate performance on two synthetic tasks: SCAN, where it outperforms previous models on the LENGTH split, and English question formation, where it performs comparably to decoders with the ground-truth tree structure. We also present experimental results on German-English translation on the Multi30k dataset, and qualitatively analyse the induced tree structures our model learns for the SCAN tasks and the German-English translation task.</abstract>
<identifier type="citekey">tan-etal-2020-recursive</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.208</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.208</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>2291</start>
<end>2307</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Recursive Top-Down Production for Sentence Generation with Latent Trees
%A Tan, Shawn
%A Shen, Yikang
%A Sordoni, Alessandro
%A Courville, Aaron
%A O’Donnell, Timothy J.
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F tan-etal-2020-recursive
%X We model the recursive production property of context-free grammars for natural and synthetic languages. To this end, we present a dynamic programming algorithm that marginalises over latent binary tree structures with N leaves, allowing us to compute the likelihood of a sequence of N tokens under a latent tree model, which we maximise to train a recursive neural function. We demonstrate performance on two synthetic tasks: SCAN, where it outperforms previous models on the LENGTH split, and English question formation, where it performs comparably to decoders with the ground-truth tree structure. We also present experimental results on German-English translation on the Multi30k dataset, and qualitatively analyse the induced tree structures our model learns for the SCAN tasks and the German-English translation task.
%R 10.18653/v1/2020.findings-emnlp.208
%U https://aclanthology.org/2020.findings-emnlp.208
%U https://doi.org/10.18653/v1/2020.findings-emnlp.208
%P 2291-2307
Markdown (Informal)
[Recursive Top-Down Production for Sentence Generation with Latent Trees](https://aclanthology.org/2020.findings-emnlp.208) (Tan et al., Findings 2020)
ACL