@inproceedings{zhao-etal-2022-keyphrase,
title = "Keyphrase Generation via Soft and Hard Semantic Corrections",
author = "Zhao, Guangzhen and
Yin, Guoshun and
Yang, Peng and
Yao, Yu",
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.529",
doi = "10.18653/v1/2022.emnlp-main.529",
pages = "7757--7768",
abstract = "Keyphrase generation aims to generate a set of condensed phrases given a source document. Although maximum likelihood estimation (MLE) based keyphrase generation methods have shown impressive performance, they suffer from the bias on the source-prediction sequence pair and the bias on the prediction-target pair. To tackle the above biases, we propose a novel correction model CorrKG on top of the MLE pipeline, where the biases are corrected via the optimal transport (OT) and a frequency-based filtering-and-sorting (FreqFS) strategy. Specifically, OT is introduced as soft correction to facilitate the alignment of salient information and rectify the semantic bias in the source document and predicted keyphrases pair. An adaptive semantic mass learning scheme is conducted on the vanilla OT to achieve a proper pair-wise optimal transport procedure, which promotes the OT learning brought by rectifying semantic masses dynamically. Besides, the FreqFS strategy is designed as hard correction to reduce the bias of predicted and ground truth keyphrases, and thus to generate accurate and sufficient keyphrases. Extensive experiments over multiple benchmark datasets show that our model achieves superior keyphrase generation as compared with the state-of-the-arts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2022-keyphrase">
<titleInfo>
<title>Keyphrase Generation via Soft and Hard Semantic Corrections</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guangzhen</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guoshun</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Yao</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>Keyphrase generation aims to generate a set of condensed phrases given a source document. Although maximum likelihood estimation (MLE) based keyphrase generation methods have shown impressive performance, they suffer from the bias on the source-prediction sequence pair and the bias on the prediction-target pair. To tackle the above biases, we propose a novel correction model CorrKG on top of the MLE pipeline, where the biases are corrected via the optimal transport (OT) and a frequency-based filtering-and-sorting (FreqFS) strategy. Specifically, OT is introduced as soft correction to facilitate the alignment of salient information and rectify the semantic bias in the source document and predicted keyphrases pair. An adaptive semantic mass learning scheme is conducted on the vanilla OT to achieve a proper pair-wise optimal transport procedure, which promotes the OT learning brought by rectifying semantic masses dynamically. Besides, the FreqFS strategy is designed as hard correction to reduce the bias of predicted and ground truth keyphrases, and thus to generate accurate and sufficient keyphrases. Extensive experiments over multiple benchmark datasets show that our model achieves superior keyphrase generation as compared with the state-of-the-arts.</abstract>
<identifier type="citekey">zhao-etal-2022-keyphrase</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.529</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.529</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>7757</start>
<end>7768</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Keyphrase Generation via Soft and Hard Semantic Corrections
%A Zhao, Guangzhen
%A Yin, Guoshun
%A Yang, Peng
%A Yao, Yu
%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 zhao-etal-2022-keyphrase
%X Keyphrase generation aims to generate a set of condensed phrases given a source document. Although maximum likelihood estimation (MLE) based keyphrase generation methods have shown impressive performance, they suffer from the bias on the source-prediction sequence pair and the bias on the prediction-target pair. To tackle the above biases, we propose a novel correction model CorrKG on top of the MLE pipeline, where the biases are corrected via the optimal transport (OT) and a frequency-based filtering-and-sorting (FreqFS) strategy. Specifically, OT is introduced as soft correction to facilitate the alignment of salient information and rectify the semantic bias in the source document and predicted keyphrases pair. An adaptive semantic mass learning scheme is conducted on the vanilla OT to achieve a proper pair-wise optimal transport procedure, which promotes the OT learning brought by rectifying semantic masses dynamically. Besides, the FreqFS strategy is designed as hard correction to reduce the bias of predicted and ground truth keyphrases, and thus to generate accurate and sufficient keyphrases. Extensive experiments over multiple benchmark datasets show that our model achieves superior keyphrase generation as compared with the state-of-the-arts.
%R 10.18653/v1/2022.emnlp-main.529
%U https://aclanthology.org/2022.emnlp-main.529
%U https://doi.org/10.18653/v1/2022.emnlp-main.529
%P 7757-7768
Markdown (Informal)
[Keyphrase Generation via Soft and Hard Semantic Corrections](https://aclanthology.org/2022.emnlp-main.529) (Zhao et al., EMNLP 2022)
ACL
- Guangzhen Zhao, Guoshun Yin, Peng Yang, and Yu Yao. 2022. Keyphrase Generation via Soft and Hard Semantic Corrections. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 7757–7768, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.