@inproceedings{chen-etal-2022-coherent,
title = "Coherent Long Text Generation by Contrastive Soft Prompt",
author = "Chen, Guandan and
Pu, Jiashu and
Xi, Yadong and
Zhang, Rongsheng",
editor = "Bosselut, Antoine and
Chandu, Khyathi and
Dhole, Kaustubh and
Gangal, Varun and
Gehrmann, Sebastian and
Jernite, Yacine and
Novikova, Jekaterina and
Perez-Beltrachini, Laura",
booktitle = "Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.gem-1.42/",
doi = "10.18653/v1/2022.gem-1.42",
pages = "445--455",
abstract = "Improving the coherence of long text generation is an important but challenging task. Existing models still struggle to generate a logical and coherent sentence sequence. It is difficult for a model to plan long text generation and avoid generating incoherent texts from a high-level semantic perspective. We speculate that this is due to two factors: (1) current training methods mainly rely on maximum likelihood estimation computed from token-level probability prediction; (2) the role of incoherent texts has been largely under-explored, thus the noised generated texts with errors are out-of-distribution for the model. To address these issues, in this paper, we propose a Contrastive Soft Prompt (CSP) model for improving the coherence of long text generation. It learns text representations in the hidden space for better planning long text generation. To this end, it jointly learns to generate a text representation close to representations of coherent texts and away from incoherent ones, and then generate long text taking this representation as the soft prompt. We conduct experiments on two public story generation datasets, and experiment results show that our method can generate more coherent stories than the state-of-the-art model."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2022-coherent">
<titleInfo>
<title>Coherent Long Text Generation by Contrastive Soft Prompt</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guandan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiashu</namePart>
<namePart type="family">Pu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yadong</namePart>
<namePart type="family">Xi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rongsheng</namePart>
<namePart type="family">Zhang</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 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bosselut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khyathi</namePart>
<namePart type="family">Chandu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaustubh</namePart>
<namePart type="family">Dhole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="family">Gangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yacine</namePart>
<namePart type="family">Jernite</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jekaterina</namePart>
<namePart type="family">Novikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Perez-Beltrachini</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 (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Improving the coherence of long text generation is an important but challenging task. Existing models still struggle to generate a logical and coherent sentence sequence. It is difficult for a model to plan long text generation and avoid generating incoherent texts from a high-level semantic perspective. We speculate that this is due to two factors: (1) current training methods mainly rely on maximum likelihood estimation computed from token-level probability prediction; (2) the role of incoherent texts has been largely under-explored, thus the noised generated texts with errors are out-of-distribution for the model. To address these issues, in this paper, we propose a Contrastive Soft Prompt (CSP) model for improving the coherence of long text generation. It learns text representations in the hidden space for better planning long text generation. To this end, it jointly learns to generate a text representation close to representations of coherent texts and away from incoherent ones, and then generate long text taking this representation as the soft prompt. We conduct experiments on two public story generation datasets, and experiment results show that our method can generate more coherent stories than the state-of-the-art model.</abstract>
<identifier type="citekey">chen-etal-2022-coherent</identifier>
<identifier type="doi">10.18653/v1/2022.gem-1.42</identifier>
<location>
<url>https://aclanthology.org/2022.gem-1.42/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>445</start>
<end>455</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Coherent Long Text Generation by Contrastive Soft Prompt
%A Chen, Guandan
%A Pu, Jiashu
%A Xi, Yadong
%A Zhang, Rongsheng
%Y Bosselut, Antoine
%Y Chandu, Khyathi
%Y Dhole, Kaustubh
%Y Gangal, Varun
%Y Gehrmann, Sebastian
%Y Jernite, Yacine
%Y Novikova, Jekaterina
%Y Perez-Beltrachini, Laura
%S Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F chen-etal-2022-coherent
%X Improving the coherence of long text generation is an important but challenging task. Existing models still struggle to generate a logical and coherent sentence sequence. It is difficult for a model to plan long text generation and avoid generating incoherent texts from a high-level semantic perspective. We speculate that this is due to two factors: (1) current training methods mainly rely on maximum likelihood estimation computed from token-level probability prediction; (2) the role of incoherent texts has been largely under-explored, thus the noised generated texts with errors are out-of-distribution for the model. To address these issues, in this paper, we propose a Contrastive Soft Prompt (CSP) model for improving the coherence of long text generation. It learns text representations in the hidden space for better planning long text generation. To this end, it jointly learns to generate a text representation close to representations of coherent texts and away from incoherent ones, and then generate long text taking this representation as the soft prompt. We conduct experiments on two public story generation datasets, and experiment results show that our method can generate more coherent stories than the state-of-the-art model.
%R 10.18653/v1/2022.gem-1.42
%U https://aclanthology.org/2022.gem-1.42/
%U https://doi.org/10.18653/v1/2022.gem-1.42
%P 445-455
Markdown (Informal)
[Coherent Long Text Generation by Contrastive Soft Prompt](https://aclanthology.org/2022.gem-1.42/) (Chen et al., GEM 2022)
ACL
- Guandan Chen, Jiashu Pu, Yadong Xi, and Rongsheng Zhang. 2022. Coherent Long Text Generation by Contrastive Soft Prompt. In Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM), pages 445–455, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.