Distantly Supervised Transformers For E-Commerce Product QA
Happy Mittal, Aniket Chakrabarti, Belhassen Bayar, Animesh Anant, Sharma, Nikhil Rasiwasia

TL;DR
This paper introduces a transformer-based QA system for e-commerce product pages that learns relevance without labeled data, combining syntactic and semantic features for improved retrieval performance.
Contribution
It presents a novel distantly supervised transformer model that jointly learns syntactic and semantic relevance for product QA, scalable for large e-commerce platforms.
Findings
Significantly outperforms baseline methods in offline evaluations.
Achieves superior results in large-scale online A/B tests.
Enables offline candidate embedding to reduce real-time computation.
Abstract
We propose a practical instant question answering (QA) system on product pages of ecommerce services, where for each user query, relevant community question answer (CQA) pairs are retrieved. User queries and CQA pairs differ significantly in language characteristics making relevance learning difficult. Our proposed transformer-based model learns a robust relevance function by jointly learning unified syntactic and semantic representations without the need for human labeled data. This is achieved by distantly supervising our model by distilling from predictions of a syntactic matching system on user queries and simultaneously training with CQA pairs. Training with CQA pairs helps our model learning semantic QA relevance and distant supervision enables learning of syntactic features as well as the nuances of user querying language. Additionally, our model encodes queries and candidate…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
Methodstravel james
