Ask Me What You Need: Product Retrieval using Knowledge from GPT-3

Autor:	Kim, Su Young, Park, Hyeonjin, Shin, Kyuyong, Kim, Kyung-Min
Rok vydání:	2022
Předmět:	Computer Science - Information Retrieval
Druh dokumentu:	Working Paper
Popis:	As online merchandise become more common, many studies focus on embedding-based methods where queries and products are represented in the semantic space. These methods alleviate the problem of vocab mismatch between the language of queries and products. However, past studies usually dealt with queries that precisely describe the product, and there still exists the need to answer imprecise queries that may require common sense knowledge, i.e., 'what should I get my mom for Mother's Day.' In this paper, we propose a GPT-3 based product retrieval system that leverages the knowledge-base (KB) of GPT-3 for question answering; users do not need to know the specific illustrative keywords for a product when querying. Our method tunes prompt tokens of GPT-3 to prompt knowledge and render answers that are mapped directly to products without further processing. Our method shows consistent performance improvement on two real-world and one public dataset, compared to the baseline methods. We provide an in-depth discussion on leveraging GPT-3 knowledge into a question answering based retrieval system. Comment: Accepted to DLP-KDD 2022 Workshop
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2207.02516 Zobrazit plný text záznamu View this record from Arxiv