Opinions Are Not Always Positive: Debiasing Opinion Summarization With Model-Specific and Model-Agnostic Methods

TY - CHAP

T1 - Opinions Are Not Always Positive

T2 - Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

AU - Zhang, Yanyue

AU - Lai, Yilong

AU - Wang, Zhenglin

AU - Li, Pengfei

AU - Zhou, Deyu

AU - He, Yulan

N1 - Publisher Copyright: © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

PY - 2024

Y1 - 2024

N2 - As in the existing opinion summary data set, more than 70% are positive texts, the current opinion summarization approaches are reluctant to generate the negative opinion summary given the input of negative opinions. To address such sentiment bias, two approaches are proposed through two perspectives: model-specific and model-agnostic. For the model-specific approach, a variational autoencoder is proposed to disentangle the input representation into sentiment-relevant and sentiment-irrelevant components through adversarial loss. Therefore, the sentiment information in the input is kept and employed for the following decoding which avoids interference of content information with emotional signals. To further avoid relying on some specific opinion summarization frameworks, a model-agnostic approach based on counterfactual data augmentation is proposed. A dataset with a more balanced emotional polarity distribution is constructed using a large pre-trained language model based on some pairwise and mini-edited principles. Experimental results show that the sentiment consistency of the generated summaries is significantly improved using the proposed approaches, while their semantics quality is unaffected.

AB - As in the existing opinion summary data set, more than 70% are positive texts, the current opinion summarization approaches are reluctant to generate the negative opinion summary given the input of negative opinions. To address such sentiment bias, two approaches are proposed through two perspectives: model-specific and model-agnostic. For the model-specific approach, a variational autoencoder is proposed to disentangle the input representation into sentiment-relevant and sentiment-irrelevant components through adversarial loss. Therefore, the sentiment information in the input is kept and employed for the following decoding which avoids interference of content information with emotional signals. To further avoid relying on some specific opinion summarization frameworks, a model-agnostic approach based on counterfactual data augmentation is proposed. A dataset with a more balanced emotional polarity distribution is constructed using a large pre-trained language model based on some pairwise and mini-edited principles. Experimental results show that the sentiment consistency of the generated summaries is significantly improved using the proposed approaches, while their semantics quality is unaffected.

KW - data augmentation

KW - disentanglement

KW - emotional bias

KW - summarization

UR - http://www.scopus.com/inward/record.url?scp=85195953882&partnerID=8YFLogxK

M3 - Conference paper

AN - SCOPUS:85195953882

T3 - 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings

SP - 12496

EP - 12513

BT - 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings

A2 - Calzolari, Nicoletta

A2 - Kan, Min-Yen

A2 - Hoste, Veronique

A2 - Lenci, Alessandro

A2 - Sakti, Sakriani

A2 - Xue, Nianwen

PB - European Language Resources Association (ELRA)

Y2 - 20 May 2024 through 25 May 2024

ER -