@inproceedings{carlsson-etal-2022-fine,
title = "Fine-Grained Controllable Text Generation Using Non-Residual Prompting",
author = {Carlsson, Fredrik and
{\"O}hman, Joey and
Liu, Fangyu and
Verlinden, Severine and
Nivre, Joakim and
Sahlgren, Magnus},
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.471",
doi = "10.18653/v1/2022.acl-long.471",
pages = "6837--6857",
abstract = "The introduction of immensely large Causal Language Models (CLMs) has rejuvenated the interest in open-ended text generation. However, controlling the generative process for these Transformer-based models is at large an unsolved problem. Earlier work has explored either plug-and-play decoding strategies, or more powerful but blunt approaches such as prompting. There hence currently exists a trade-off between fine-grained control, and the capability for more expressive high-level instructions. To alleviate this trade-off, we propose an encoder-decoder architecture that enables intermediate text prompts at arbitrary time steps. We propose a resource-efficient method for converting a pre-trained CLM into this architecture, and demonstrate its potential on various experiments, including the novel task of contextualized word inclusion. Our method provides strong results on multiple experimental settings, proving itself to be both expressive and versatile.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="carlsson-etal-2022-fine">
<titleInfo>
<title>Fine-Grained Controllable Text Generation Using Non-Residual Prompting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fredrik</namePart>
<namePart type="family">Carlsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joey</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fangyu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Severine</namePart>
<namePart type="family">Verlinden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joakim</namePart>
<namePart type="family">Nivre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Magnus</namePart>
<namePart type="family">Sahlgren</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>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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 introduction of immensely large Causal Language Models (CLMs) has rejuvenated the interest in open-ended text generation. However, controlling the generative process for these Transformer-based models is at large an unsolved problem. Earlier work has explored either plug-and-play decoding strategies, or more powerful but blunt approaches such as prompting. There hence currently exists a trade-off between fine-grained control, and the capability for more expressive high-level instructions. To alleviate this trade-off, we propose an encoder-decoder architecture that enables intermediate text prompts at arbitrary time steps. We propose a resource-efficient method for converting a pre-trained CLM into this architecture, and demonstrate its potential on various experiments, including the novel task of contextualized word inclusion. Our method provides strong results on multiple experimental settings, proving itself to be both expressive and versatile.</abstract>
<identifier type="citekey">carlsson-etal-2022-fine</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.471</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.471</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>6837</start>
<end>6857</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Fine-Grained Controllable Text Generation Using Non-Residual Prompting
%A Carlsson, Fredrik
%A Öhman, Joey
%A Liu, Fangyu
%A Verlinden, Severine
%A Nivre, Joakim
%A Sahlgren, Magnus
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F carlsson-etal-2022-fine
%X The introduction of immensely large Causal Language Models (CLMs) has rejuvenated the interest in open-ended text generation. However, controlling the generative process for these Transformer-based models is at large an unsolved problem. Earlier work has explored either plug-and-play decoding strategies, or more powerful but blunt approaches such as prompting. There hence currently exists a trade-off between fine-grained control, and the capability for more expressive high-level instructions. To alleviate this trade-off, we propose an encoder-decoder architecture that enables intermediate text prompts at arbitrary time steps. We propose a resource-efficient method for converting a pre-trained CLM into this architecture, and demonstrate its potential on various experiments, including the novel task of contextualized word inclusion. Our method provides strong results on multiple experimental settings, proving itself to be both expressive and versatile.
%R 10.18653/v1/2022.acl-long.471
%U https://aclanthology.org/2022.acl-long.471
%U https://doi.org/10.18653/v1/2022.acl-long.471
%P 6837-6857
Markdown (Informal)
[Fine-Grained Controllable Text Generation Using Non-Residual Prompting](https://aclanthology.org/2022.acl-long.471) (Carlsson et al., ACL 2022)
ACL
- Fredrik Carlsson, Joey Öhman, Fangyu Liu, Severine Verlinden, Joakim Nivre, and Magnus Sahlgren. 2022. Fine-Grained Controllable Text Generation Using Non-Residual Prompting. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6837–6857, Dublin, Ireland. Association for Computational Linguistics.