Aspect-based summarization of pros and cons in unstructured product reviews

TY - CHAP

T1 - Aspect-based summarization of pros and cons in unstructured product reviews

AU - Kunneman, Florian

AU - Wubben, Sander

AU - Krahmer, Emiel

AU - van den Bosch, A.

PY - 2018/8/20

Y1 - 2018/8/20

N2 - We developed three systems for generating pros and cons summaries of product reviews. Automating this task eases the writing of product reviews, and offers readers quick access to the most important information. We compared SynPat, a system based on syntactic phrases selected on the basis of valence scores, against a neural-network-based system trained to map bag-ofwordsrepresentations of reviews directly to pros and cons, and the same neural system trained on clusters of word-embedding encodings of similar pros and cons. We evaluated the systems in two ways: first on held-out reviews with gold-standard pros and cons, and second by asking human annotators to rate the systems’ output on relevance and completeness. In the second evaluation,the gold-standard pros and cons were assessed along with the system output. We find that the human-generated summaries are not deemed as significantly more relevant or complete than the SynPat systems; the latter are scored higher than the human-generated summaries on a precision metric. The neural approaches yield a lower performance in the human assessment,and are outperformed by the baseline.

AB - We developed three systems for generating pros and cons summaries of product reviews. Automating this task eases the writing of product reviews, and offers readers quick access to the most important information. We compared SynPat, a system based on syntactic phrases selected on the basis of valence scores, against a neural-network-based system trained to map bag-ofwordsrepresentations of reviews directly to pros and cons, and the same neural system trained on clusters of word-embedding encodings of similar pros and cons. We evaluated the systems in two ways: first on held-out reviews with gold-standard pros and cons, and second by asking human annotators to rate the systems’ output on relevance and completeness. In the second evaluation,the gold-standard pros and cons were assessed along with the system output. We find that the human-generated summaries are not deemed as significantly more relevant or complete than the SynPat systems; the latter are scored higher than the human-generated summaries on a precision metric. The neural approaches yield a lower performance in the human assessment,and are outperformed by the baseline.

M3 - Contribution to conference proceedings

SP - 2219

BT - Proceedings of the 27th International Conference on Computational Linguistics

CY - Santa Fe, New Mexico, USA

ER -