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

Florian Kunneman, Sander Wubben, Emiel Krahmer, A. van den Bosch

Onderzoeksoutput: Hoofdstuk in boek/boekdeelBijdrage aan conferentie proceedingsWetenschappelijkpeer review

Samenvatting

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-ofwords
representations 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.
Originele taal-2Engels
TitelProceedings of the 27th International Conference on Computational Linguistics
Plaats van productieSanta Fe, New Mexico, USA
Pagina's2219
Aantal pagina's2229
StatusGepubliceerd - 20 aug 2018

Vingerafdruk Duik in de onderzoeksthema's van 'Aspect-based summarization of pros and cons in unstructured product reviews'. Samen vormen ze een unieke vingerafdruk.

Citeer dit