@inproceedings{madaan-etal-2022-conditional,
title = "Conditional set generation using Seq2seq models",
author = "Madaan, Aman and
Rajagopal, Dheeraj and
Tandon, Niket and
Yang, Yiming and
Bosselut, Antoine",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.324",
doi = "10.18653/v1/2022.emnlp-main.324",
pages = "4874--4896",
abstract = "Conditional set generation learns a mapping from an input sequence of tokens to a set. Several NLP tasks, such as entity typing and dialogue emotion tagging, are instances of set generation. Seq2Seq models are a popular choice to model set generation but they treat a set as a sequence and do not fully leverage its key properties, namely order-invariance and cardinality. We propose a novel algorithm for effectively sampling informative orders over the combinatorial space of label orders. Further, we jointly model the set cardinality and output by listing the set size as the first element and taking advantage of the autoregressive factorization used by Seq2Seq models. Our method is a model-independent data augmentation approach that endows any Seq2Seq model with the signals of order-invariance and cardinality. Training a Seq2Seq model on this new augmented data (without any additional annotations), gets an average relative improvement of 20{\%} for four benchmarks datasets across models spanning from BART-base, T5-11B, and GPT-3. We will release all code and data upon acceptance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="madaan-etal-2022-conditional">
<titleInfo>
<title>Conditional set generation using Seq2seq models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aman</namePart>
<namePart type="family">Madaan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dheeraj</namePart>
<namePart type="family">Rajagopal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niket</namePart>
<namePart type="family">Tandon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bosselut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Conditional set generation learns a mapping from an input sequence of tokens to a set. Several NLP tasks, such as entity typing and dialogue emotion tagging, are instances of set generation. Seq2Seq models are a popular choice to model set generation but they treat a set as a sequence and do not fully leverage its key properties, namely order-invariance and cardinality. We propose a novel algorithm for effectively sampling informative orders over the combinatorial space of label orders. Further, we jointly model the set cardinality and output by listing the set size as the first element and taking advantage of the autoregressive factorization used by Seq2Seq models. Our method is a model-independent data augmentation approach that endows any Seq2Seq model with the signals of order-invariance and cardinality. Training a Seq2Seq model on this new augmented data (without any additional annotations), gets an average relative improvement of 20% for four benchmarks datasets across models spanning from BART-base, T5-11B, and GPT-3. We will release all code and data upon acceptance.</abstract>
<identifier type="citekey">madaan-etal-2022-conditional</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.324</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.324</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>4874</start>
<end>4896</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Conditional set generation using Seq2seq models
%A Madaan, Aman
%A Rajagopal, Dheeraj
%A Tandon, Niket
%A Yang, Yiming
%A Bosselut, Antoine
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F madaan-etal-2022-conditional
%X Conditional set generation learns a mapping from an input sequence of tokens to a set. Several NLP tasks, such as entity typing and dialogue emotion tagging, are instances of set generation. Seq2Seq models are a popular choice to model set generation but they treat a set as a sequence and do not fully leverage its key properties, namely order-invariance and cardinality. We propose a novel algorithm for effectively sampling informative orders over the combinatorial space of label orders. Further, we jointly model the set cardinality and output by listing the set size as the first element and taking advantage of the autoregressive factorization used by Seq2Seq models. Our method is a model-independent data augmentation approach that endows any Seq2Seq model with the signals of order-invariance and cardinality. Training a Seq2Seq model on this new augmented data (without any additional annotations), gets an average relative improvement of 20% for four benchmarks datasets across models spanning from BART-base, T5-11B, and GPT-3. We will release all code and data upon acceptance.
%R 10.18653/v1/2022.emnlp-main.324
%U https://aclanthology.org/2022.emnlp-main.324
%U https://doi.org/10.18653/v1/2022.emnlp-main.324
%P 4874-4896
Markdown (Informal)
[Conditional set generation using Seq2seq models](https://aclanthology.org/2022.emnlp-main.324) (Madaan et al., EMNLP 2022)
ACL
- Aman Madaan, Dheeraj Rajagopal, Niket Tandon, Yiming Yang, and Antoine Bosselut. 2022. Conditional set generation using Seq2seq models. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4874–4896, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.