@inproceedings{rush-2020-torch,
title = "Torch-Struct: Deep Structured Prediction Library",
author = "Rush, Alexander",
editor = "Celikyilmaz, Asli and
Wen, Tsung-Hsien",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-demos.38/",
doi = "10.18653/v1/2020.acl-demos.38",
pages = "335--342",
abstract = "The literature on structured prediction for NLP describes a rich collection of distributions and algorithms over sequences, segmentations, alignments, and trees; however, these algorithms are difficult to utilize in deep learning frameworks. We introduce Torch-Struct, a library for structured prediction designed to take advantage of and integrate with vectorized, auto-differentiation based frameworks. Torch-Struct includes a broad collection of probabilistic structures accessed through a simple and flexible distribution-based API that connects to any deep learning model. The library utilizes batched, vectorized operations and exploits auto-differentiation to produce readable, fast, and testable code. Internally, we also include a number of general-purpose optimizations to provide cross-algorithm efficiency. Experiments show significant performance gains over fast baselines and case-studies demonstrate the benefits of the library. Torch-Struct is available at \url{https://github.com/harvardnlp/pytorch-struct}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rush-2020-torch">
<titleInfo>
<title>Torch-Struct: Deep Structured Prediction Library</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Rush</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Celikyilmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tsung-Hsien</namePart>
<namePart type="family">Wen</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 literature on structured prediction for NLP describes a rich collection of distributions and algorithms over sequences, segmentations, alignments, and trees; however, these algorithms are difficult to utilize in deep learning frameworks. We introduce Torch-Struct, a library for structured prediction designed to take advantage of and integrate with vectorized, auto-differentiation based frameworks. Torch-Struct includes a broad collection of probabilistic structures accessed through a simple and flexible distribution-based API that connects to any deep learning model. The library utilizes batched, vectorized operations and exploits auto-differentiation to produce readable, fast, and testable code. Internally, we also include a number of general-purpose optimizations to provide cross-algorithm efficiency. Experiments show significant performance gains over fast baselines and case-studies demonstrate the benefits of the library. Torch-Struct is available at https://github.com/harvardnlp/pytorch-struct.</abstract>
<identifier type="citekey">rush-2020-torch</identifier>
<identifier type="doi">10.18653/v1/2020.acl-demos.38</identifier>
<location>
<url>https://aclanthology.org/2020.acl-demos.38/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>335</start>
<end>342</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Torch-Struct: Deep Structured Prediction Library
%A Rush, Alexander
%Y Celikyilmaz, Asli
%Y Wen, Tsung-Hsien
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F rush-2020-torch
%X The literature on structured prediction for NLP describes a rich collection of distributions and algorithms over sequences, segmentations, alignments, and trees; however, these algorithms are difficult to utilize in deep learning frameworks. We introduce Torch-Struct, a library for structured prediction designed to take advantage of and integrate with vectorized, auto-differentiation based frameworks. Torch-Struct includes a broad collection of probabilistic structures accessed through a simple and flexible distribution-based API that connects to any deep learning model. The library utilizes batched, vectorized operations and exploits auto-differentiation to produce readable, fast, and testable code. Internally, we also include a number of general-purpose optimizations to provide cross-algorithm efficiency. Experiments show significant performance gains over fast baselines and case-studies demonstrate the benefits of the library. Torch-Struct is available at https://github.com/harvardnlp/pytorch-struct.
%R 10.18653/v1/2020.acl-demos.38
%U https://aclanthology.org/2020.acl-demos.38/
%U https://doi.org/10.18653/v1/2020.acl-demos.38
%P 335-342
Markdown (Informal)
[Torch-Struct: Deep Structured Prediction Library](https://aclanthology.org/2020.acl-demos.38/) (Rush, ACL 2020)
ACL
- Alexander Rush. 2020. Torch-Struct: Deep Structured Prediction Library. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 335–342, Online. Association for Computational Linguistics.