Unlocking Markets: A Multilingual Benchmark to Cross-Market Question Answering
This work addresses the challenge of providing accurate answers to product questions in e-commerce platforms, which is incremental as it extends existing PQA tasks to multilingual and cross-market settings.
The paper tackles the problem of product-related question answering in e-commerce by proposing a multilingual cross-market task, introducing a dataset of over 7 million questions from 17 marketplaces across 11 languages, and showing that using cross-market information significantly improves performance in answer generation and question ranking tasks.
Users post numerous product-related questions on e-commerce platforms, affecting their purchase decisions. Product-related question answering (PQA) entails utilizing product-related resources to provide precise responses to users. We propose a novel task of Multilingual Cross-market Product-based Question Answering (MCPQA) and define the task as providing answers to product-related questions in a main marketplace by utilizing information from another resource-rich auxiliary marketplace in a multilingual context. We introduce a large-scale dataset comprising over 7 million questions from 17 marketplaces across 11 languages. We then perform automatic translation on the Electronics category of our dataset, naming it as McMarket. We focus on two subtasks: review-based answer generation and product-related question ranking. For each subtask, we label a subset of McMarket using an LLM and further evaluate the quality of the annotations via human assessment. We then conduct experiments to benchmark our dataset, using models ranging from traditional lexical models to LLMs in both single-market and cross-market scenarios across McMarket and the corresponding LLM subset. Results show that incorporating cross-market information significantly enhances performance in both tasks.