@inproceedings{zmigrod-etal-2021-efficient,
title = "Efficient Sampling of Dependency Structure",
author = "Zmigrod, Ran and
Vieira, Tim and
Cotterell, Ryan",
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.824",
doi = "10.18653/v1/2021.emnlp-main.824",
pages = "10558--10569",
abstract = "Probabilistic distributions over spanning trees in directed graphs are a fundamental model of dependency structure in natural language processing, syntactic dependency trees. In NLP, dependency trees often have an additional root constraint: only one edge may emanate from the root. However, no sampling algorithm has been presented in the literature to account for this additional constraint. In this paper, we adapt two spanning tree sampling algorithms to faithfully sample dependency trees from a graph subject to the root constraint. Wilson (1996({'}s sampling algorithm has a running time of O(H) where H is the mean hitting time of the graph. Colbourn (1996){'}s sampling algorithm has a running time of O(N{\^{}}3), which is often greater than the mean hitting time of a directed graph. Additionally, we build upon Colbourn{'}s algorithm and present a novel extension that can sample K trees without replacement in O(K N{\^{}}3 + K{\^{}}2 N) time. To the best of our knowledge, no algorithm has been given for sampling spanning trees without replacement from a directed graph.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zmigrod-etal-2021-efficient">
<titleInfo>
<title>Efficient Sampling of Dependency Structure</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ran</namePart>
<namePart type="family">Zmigrod</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Vieira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</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>Probabilistic distributions over spanning trees in directed graphs are a fundamental model of dependency structure in natural language processing, syntactic dependency trees. In NLP, dependency trees often have an additional root constraint: only one edge may emanate from the root. However, no sampling algorithm has been presented in the literature to account for this additional constraint. In this paper, we adapt two spanning tree sampling algorithms to faithfully sample dependency trees from a graph subject to the root constraint. Wilson (1996(’s sampling algorithm has a running time of O(H) where H is the mean hitting time of the graph. Colbourn (1996)’s sampling algorithm has a running time of O(N\³), which is often greater than the mean hitting time of a directed graph. Additionally, we build upon Colbourn’s algorithm and present a novel extension that can sample K trees without replacement in O(K N\³ + K\² N) time. To the best of our knowledge, no algorithm has been given for sampling spanning trees without replacement from a directed graph.</abstract>
<identifier type="citekey">zmigrod-etal-2021-efficient</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.824</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.824</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>10558</start>
<end>10569</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Sampling of Dependency Structure
%A Zmigrod, Ran
%A Vieira, Tim
%A Cotterell, Ryan
%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 zmigrod-etal-2021-efficient
%X Probabilistic distributions over spanning trees in directed graphs are a fundamental model of dependency structure in natural language processing, syntactic dependency trees. In NLP, dependency trees often have an additional root constraint: only one edge may emanate from the root. However, no sampling algorithm has been presented in the literature to account for this additional constraint. In this paper, we adapt two spanning tree sampling algorithms to faithfully sample dependency trees from a graph subject to the root constraint. Wilson (1996(’s sampling algorithm has a running time of O(H) where H is the mean hitting time of the graph. Colbourn (1996)’s sampling algorithm has a running time of O(N\³), which is often greater than the mean hitting time of a directed graph. Additionally, we build upon Colbourn’s algorithm and present a novel extension that can sample K trees without replacement in O(K N\³ + K\² N) time. To the best of our knowledge, no algorithm has been given for sampling spanning trees without replacement from a directed graph.
%R 10.18653/v1/2021.emnlp-main.824
%U https://aclanthology.org/2021.emnlp-main.824
%U https://doi.org/10.18653/v1/2021.emnlp-main.824
%P 10558-10569
Markdown (Informal)
[Efficient Sampling of Dependency Structure](https://aclanthology.org/2021.emnlp-main.824) (Zmigrod et al., EMNLP 2021)
ACL
- Ran Zmigrod, Tim Vieira, and Ryan Cotterell. 2021. Efficient Sampling of Dependency Structure. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10558–10569, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.