DeepAI AI Chat
Log In Sign Up

Semantic Product Search

by   Priyanka Nigam, et al.
Carnegie Mellon University

We study the problem of semantic matching in product search, that is, given a customer query, retrieve all semantically related products from the catalog. Pure lexical matching via an inverted index falls short in this respect due to several factors: a) lack of understanding of hypernyms, synonyms, and antonyms, b) fragility to morphological variants (e.g. "woman" vs. "women"), and c) sensitivity to spelling errors. To address these issues, we train a deep learning model for semantic matching using customer behavior data. Much of the recent work on large-scale semantic search using deep learning focuses on ranking for web search. In contrast, semantic matching for product search presents several novel challenges, which we elucidate in this paper. We address these challenges by a) developing a new loss function that has an inbuilt threshold to differentiate between random negative examples, impressed but not purchased examples, and positive examples (purchased items), b) using average pooling in conjunction with n-grams to capture short-range linguistic patterns, c) using hashing to handle out of vocabulary tokens, and d) using a model parallel training architecture to scale across 8 GPUs. We present compelling offline results that demonstrate at least 4.7 14.5 state-of-the-art semantic search methods using the same tokenization method. Moreover, we present results and discuss learnings from online A/B tests which demonstrate the efficacy of our method.


Extreme Multi-label Learning for Semantic Matching in Product Search

We consider the problem of semantic matching in product search: given a ...

Embracing Structure in Data for Billion-Scale Semantic Product Search

We present principled approaches to train and deploy dyadic neural embed...

Semantic Product Search for Matching Structured Product Catalogs in E-Commerce

Retrieving all semantically relevant products from the product catalog i...

Intent-based Product Collections for E-commerce using Pretrained Language Models

Building a shopping product collection has been primarily a human job. W...

Scalable Semantic Matching of Queries to Ads in Sponsored Search Advertising

Sponsored search represents a major source of revenue for web search eng...

AdsGNN: Behavior-Graph Augmented Relevance Modeling in Sponsored Search

Sponsored search ads appear next to search results when people look for ...

Optimizing Airbnb Search Journey with Multi-task Learning

At Airbnb, an online marketplace for stays and experiences, guests often...

Code Repositories


A Javascript plugin for a universal search box with search suggestion - no jQuery required.

view repo


A Javascript jQuery Plugin for a universal search box with search suggestion.

view repo


A Javascript jQuery Plugin for a universal search box with search suggestion.

view repo