Near-Zero-Shot Suggestion Mining with a Little Help from WordNet
This work addresses the need for cost-effective suggestion mining in user-generated content, offering a practical solution for businesses and researchers with incremental advancements in zero-shot classification.
The paper tackled the problem of classifying suggestions in online reviews with minimal training data by developing entailment-based zero-shot approaches, achieving significant improvements in prediction quality through a novel label assignment strategy.
In this work, we explore the constructive side of online reviews: advice, tips, requests, and suggestions that users provide about goods, venues, services, and other items of interest. To reduce training costs and annotation efforts needed to build a classifier for a specific label set, we present and evaluate several entailment-based zero-shot approaches to suggestion classification in a label-fully-unseen fashion. In particular, we introduce the strategy of assigning target class labels to sentences in English language with user intentions, which significantly improves prediction quality. The proposed strategies are evaluated with a comprehensive experimental study that validated our results both quantitatively and qualitatively.