Semantic Product Search

Abstract

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% improvement in Recall@100 and 14.5% improvement in mean average precision (MAP) over baseline 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.

10 pages, 7 figures, KDD 2019 (Applied Data Science Track)

References in corpus (7)

• Distributed Representations of Words and Phrases and their Compositionality
• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• A Deep Relevance Matching Model for Ad-hoc Retrieval
• Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN
• A Dual Embedding Space Model for Document Ranking
• Query Expansion with Locally-Trained Word Embeddings
• Feature Hashing for Large Scale Multitask Learning

Cited by in corpus (10)

• Learning a Product Relevance Model from Click-Through Data in E-Commerce
• Leveraging Semantic and Lexical Matching to Improve the Recall of Document Retrieval Systems: A Hybrid Approach
• Graph Reordering for Cache-Efficient Near Neighbor Search
• Heterogeneous Network Embedding for Deep Semantic Relevance Match in E-commerce Search
• Semantic Product Search for Matching Structured Product Catalogs in E-Commerce
• Embedding-based Product Retrieval in Taobao Search
• Evaluation of Field-Aware Neural Ranking Models for Recipe Search
• Non-Linear Multiple Field Interactions Neural Document Ranking
• Low-Precision Quantization for Efficient Nearest Neighbor Search
• Extreme Multi-label Learning for Semantic Matching in Product Search