@inproceedings{landsman-etal-2022-beamr,
title = "{B}eam{R}: Beam Reweighing with Attribute Discriminators for Controllable Text Generation",
author = "Landsman, David and
Chen, Jerry Zikun and
Zaidi, Hussain",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-aacl.40",
pages = "422--437",
abstract = "Recent advances in natural language processing have led to the availability of large pre-trained language models (LMs), with rich generative capabilities. Although these models are able to produce fluent and coherent text, it remains a challenge to control various attributes of the generation, including sentiment, formality, topic and many others. We propose a Beam Reweighing (BeamR) method, building on top of standard beam search, in order to control different attributes. BeamR combines any generative LM with any attribute discriminator, offering full flexibility of generation style and attribute, while the beam search backbone maintains fluency across different domains. Notably, BeamR allows practitioners to leverage pre-trained models without the need to train generative LMs together with discriminators. We evaluate BeamR in two diverse tasks: sentiment steering, and machine translation formality. Our results show that BeamR performs on par with or better than existing state-of-the-art approaches (including fine-tuned methods), and highlight the flexiblity of BeamR in both causal and seq2seq language modeling tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="landsman-etal-2022-beamr">
<titleInfo>
<title>BeamR: Beam Reweighing with Attribute Discriminators for Controllable Text Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Landsman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jerry</namePart>
<namePart type="given">Zikun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hussain</namePart>
<namePart type="family">Zaidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in natural language processing have led to the availability of large pre-trained language models (LMs), with rich generative capabilities. Although these models are able to produce fluent and coherent text, it remains a challenge to control various attributes of the generation, including sentiment, formality, topic and many others. We propose a Beam Reweighing (BeamR) method, building on top of standard beam search, in order to control different attributes. BeamR combines any generative LM with any attribute discriminator, offering full flexibility of generation style and attribute, while the beam search backbone maintains fluency across different domains. Notably, BeamR allows practitioners to leverage pre-trained models without the need to train generative LMs together with discriminators. We evaluate BeamR in two diverse tasks: sentiment steering, and machine translation formality. Our results show that BeamR performs on par with or better than existing state-of-the-art approaches (including fine-tuned methods), and highlight the flexiblity of BeamR in both causal and seq2seq language modeling tasks.</abstract>
<identifier type="citekey">landsman-etal-2022-beamr</identifier>
<location>
<url>https://aclanthology.org/2022.findings-aacl.40</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>422</start>
<end>437</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BeamR: Beam Reweighing with Attribute Discriminators for Controllable Text Generation
%A Landsman, David
%A Chen, Jerry Zikun
%A Zaidi, Hussain
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F landsman-etal-2022-beamr
%X Recent advances in natural language processing have led to the availability of large pre-trained language models (LMs), with rich generative capabilities. Although these models are able to produce fluent and coherent text, it remains a challenge to control various attributes of the generation, including sentiment, formality, topic and many others. We propose a Beam Reweighing (BeamR) method, building on top of standard beam search, in order to control different attributes. BeamR combines any generative LM with any attribute discriminator, offering full flexibility of generation style and attribute, while the beam search backbone maintains fluency across different domains. Notably, BeamR allows practitioners to leverage pre-trained models without the need to train generative LMs together with discriminators. We evaluate BeamR in two diverse tasks: sentiment steering, and machine translation formality. Our results show that BeamR performs on par with or better than existing state-of-the-art approaches (including fine-tuned methods), and highlight the flexiblity of BeamR in both causal and seq2seq language modeling tasks.
%U https://aclanthology.org/2022.findings-aacl.40
%P 422-437
Markdown (Informal)
[BeamR: Beam Reweighing with Attribute Discriminators for Controllable Text Generation](https://aclanthology.org/2022.findings-aacl.40) (Landsman et al., Findings 2022)
ACL