@inproceedings{simig-etal-2022-open,
title = "Open Vocabulary Extreme Classification Using Generative Models",
author = "Simig, Daniel and
Petroni, Fabio and
Yanki, Pouya and
Popat, Kashyap and
Du, Christina and
Riedel, Sebastian and
Yazdani, Majid",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.123/",
doi = "10.18653/v1/2022.findings-acl.123",
pages = "1561--1583",
abstract = "The extreme multi-label classification (XMC) task aims at tagging content with a subset of labels from an extremely large label set. The label vocabulary is typically defined in advance by domain experts and assumed to capture all necessary tags. However in real world scenarios this label set, although large, is often incomplete and experts frequently need to refine it. To develop systems that simplify this process, we introduce the task of open vocabulary XMC (OXMC): given a piece of content, predict a set of labels, some of which may be outside of the known tag set. Hence, in addition to not having training data for some labels{--}as is the case in zero-shot classification{--}models need to invent some labels on-thefly. We propose GROOV, a fine-tuned seq2seq model for OXMC that generates the set of labels as a flat sequence and is trained using a novel loss independent of predicted label order. We show the efficacy of the approach, experimenting with popular XMC datasets for which GROOV is able to predict meaningful labels outside the given vocabulary while performing on par with state-of-the-art solutions for known labels."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simig-etal-2022-open">
<titleInfo>
<title>Open Vocabulary Extreme Classification Using Generative Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Simig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Petroni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pouya</namePart>
<namePart type="family">Yanki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kashyap</namePart>
<namePart type="family">Popat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christina</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Riedel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Majid</namePart>
<namePart type="family">Yazdani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The extreme multi-label classification (XMC) task aims at tagging content with a subset of labels from an extremely large label set. The label vocabulary is typically defined in advance by domain experts and assumed to capture all necessary tags. However in real world scenarios this label set, although large, is often incomplete and experts frequently need to refine it. To develop systems that simplify this process, we introduce the task of open vocabulary XMC (OXMC): given a piece of content, predict a set of labels, some of which may be outside of the known tag set. Hence, in addition to not having training data for some labels–as is the case in zero-shot classification–models need to invent some labels on-thefly. We propose GROOV, a fine-tuned seq2seq model for OXMC that generates the set of labels as a flat sequence and is trained using a novel loss independent of predicted label order. We show the efficacy of the approach, experimenting with popular XMC datasets for which GROOV is able to predict meaningful labels outside the given vocabulary while performing on par with state-of-the-art solutions for known labels.</abstract>
<identifier type="citekey">simig-etal-2022-open</identifier>
<identifier type="doi">10.18653/v1/2022.findings-acl.123</identifier>
<location>
<url>https://aclanthology.org/2022.findings-acl.123/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>1561</start>
<end>1583</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Open Vocabulary Extreme Classification Using Generative Models
%A Simig, Daniel
%A Petroni, Fabio
%A Yanki, Pouya
%A Popat, Kashyap
%A Du, Christina
%A Riedel, Sebastian
%A Yazdani, Majid
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F simig-etal-2022-open
%X The extreme multi-label classification (XMC) task aims at tagging content with a subset of labels from an extremely large label set. The label vocabulary is typically defined in advance by domain experts and assumed to capture all necessary tags. However in real world scenarios this label set, although large, is often incomplete and experts frequently need to refine it. To develop systems that simplify this process, we introduce the task of open vocabulary XMC (OXMC): given a piece of content, predict a set of labels, some of which may be outside of the known tag set. Hence, in addition to not having training data for some labels–as is the case in zero-shot classification–models need to invent some labels on-thefly. We propose GROOV, a fine-tuned seq2seq model for OXMC that generates the set of labels as a flat sequence and is trained using a novel loss independent of predicted label order. We show the efficacy of the approach, experimenting with popular XMC datasets for which GROOV is able to predict meaningful labels outside the given vocabulary while performing on par with state-of-the-art solutions for known labels.
%R 10.18653/v1/2022.findings-acl.123
%U https://aclanthology.org/2022.findings-acl.123/
%U https://doi.org/10.18653/v1/2022.findings-acl.123
%P 1561-1583
Markdown (Informal)
[Open Vocabulary Extreme Classification Using Generative Models](https://aclanthology.org/2022.findings-acl.123/) (Simig et al., Findings 2022)
ACL
- Daniel Simig, Fabio Petroni, Pouya Yanki, Kashyap Popat, Christina Du, Sebastian Riedel, and Majid Yazdani. 2022. Open Vocabulary Extreme Classification Using Generative Models. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1561–1583, Dublin, Ireland. Association for Computational Linguistics.