Litcius/Paper detail

Calibration Learning for Few-shot Novel Product Description

Zheng Liu, WU Ming-jing, B Peng, Yichao Liu, Qi Peng, Chong Zou

202330 citationsDOI

Abstract

In the field of E-commerce, the rapid introduction of new products poses challenges for product description generation. Traditional approaches rely on large labelled datasets, which are often unavailable for novel products with limited data. To address this issue, we propose a calibration learning approach for few-shot novel product description. Our method leverages a small amount of labelled data for calibration and utilizes the novel product's semantic representation as prompts to generate accurate and informative descriptions. We evaluate our approach on three large-scale e-commerce datasets of novel products and demonstrate its effectiveness in significantly improving the quality of generated product descriptions compared to existing methods, especially when only limited data is available. We also conduct the analysis to understand the impact of different modules on the performance.

Topics & Concepts

Computer scienceCalibrationProduct (mathematics)Representation (politics)Quality (philosophy)Field (mathematics)Machine learningArtificial intelligenceScale (ratio)Data miningInformation retrievalMathematicsPolitical scienceStatisticsLawPure mathematicsGeometryQuantum mechanicsPoliticsEpistemologyPhilosophyPhysicsSentiment Analysis and Opinion MiningMultimodal Machine Learning ApplicationsText and Document Classification Technologies
Calibration Learning for Few-shot Novel Product Description | Litcius