@inproceedings{xu-etal-2022-prince,
title = "{PRINCE}: Prefix-Masked Decoding for Knowledge Enhanced Sequence-to-Sequence Pre-Training",
author = "Xu, Song and
Li, Haoran and
Yuan, Peng and
Wu, Youzheng and
He, Xiaodong",
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.171",
doi = "10.18653/v1/2022.emnlp-main.171",
pages = "2675--2681",
abstract = "Pre-trained Language Models (PLMs) have shown effectiveness in various Natural Language Processing (NLP) tasks. Denoising autoencoder is one of the most successful pre-training frameworks, learning to recompose the original text given a noise-corrupted one. The existing studies mainly focus on injecting noises into the input. This paper introduces a simple yet effective pre-training paradigm, equipped with a knowledge-enhanced decoder that predicts the next entity token with noises in the prefix, explicitly strengthening the representation learning of entities that span over multiple input tokens. Specifically, when predicting the next token within an entity, we feed masks into the prefix in place of some of the previous ground-truth tokens that constitute the entity. Our model achieves new state-of-the-art results on two knowledge-driven data-to-text generation tasks with up to 2{\%} BLEU gains.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2022-prince">
<titleInfo>
<title>PRINCE: Prefix-Masked Decoding for Knowledge Enhanced Sequence-to-Sequence Pre-Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Song</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoran</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youzheng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodong</namePart>
<namePart type="family">He</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>Pre-trained Language Models (PLMs) have shown effectiveness in various Natural Language Processing (NLP) tasks. Denoising autoencoder is one of the most successful pre-training frameworks, learning to recompose the original text given a noise-corrupted one. The existing studies mainly focus on injecting noises into the input. This paper introduces a simple yet effective pre-training paradigm, equipped with a knowledge-enhanced decoder that predicts the next entity token with noises in the prefix, explicitly strengthening the representation learning of entities that span over multiple input tokens. Specifically, when predicting the next token within an entity, we feed masks into the prefix in place of some of the previous ground-truth tokens that constitute the entity. Our model achieves new state-of-the-art results on two knowledge-driven data-to-text generation tasks with up to 2% BLEU gains.</abstract>
<identifier type="citekey">xu-etal-2022-prince</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.171</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.171</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>2675</start>
<end>2681</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PRINCE: Prefix-Masked Decoding for Knowledge Enhanced Sequence-to-Sequence Pre-Training
%A Xu, Song
%A Li, Haoran
%A Yuan, Peng
%A Wu, Youzheng
%A He, Xiaodong
%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 xu-etal-2022-prince
%X Pre-trained Language Models (PLMs) have shown effectiveness in various Natural Language Processing (NLP) tasks. Denoising autoencoder is one of the most successful pre-training frameworks, learning to recompose the original text given a noise-corrupted one. The existing studies mainly focus on injecting noises into the input. This paper introduces a simple yet effective pre-training paradigm, equipped with a knowledge-enhanced decoder that predicts the next entity token with noises in the prefix, explicitly strengthening the representation learning of entities that span over multiple input tokens. Specifically, when predicting the next token within an entity, we feed masks into the prefix in place of some of the previous ground-truth tokens that constitute the entity. Our model achieves new state-of-the-art results on two knowledge-driven data-to-text generation tasks with up to 2% BLEU gains.
%R 10.18653/v1/2022.emnlp-main.171
%U https://aclanthology.org/2022.emnlp-main.171
%U https://doi.org/10.18653/v1/2022.emnlp-main.171
%P 2675-2681
Markdown (Informal)
[PRINCE: Prefix-Masked Decoding for Knowledge Enhanced Sequence-to-Sequence Pre-Training](https://aclanthology.org/2022.emnlp-main.171) (Xu et al., EMNLP 2022)
ACL