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 stateof-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.

Cross-Lingual Document Retrieval with Smooth Learning

“…In addition, CNN and LSTM are more difficult to optimize, as they require more computational resources, training time, and tend to overfit. Our results are in accordance with the findings in Nigam et al [2019]'s study.…”

“…The benefits of this model are in two folds: on one hand, despite non-linearity, the models are smooth and Lipschitz continuous with respect to embedding parameters, and therefore benefits from convergence of generalization error during training; on the other hand, using average pooling avoids extra parameters in the model, thus simplifies the model space and reduces tuning efforts during training, in accordance to the findings in Nigam et al [2019]'s work.…”

“…Shen et al [2014] and Palangi et al [2016] extended the feed-forward structure in DSSM to convolutional neural networks (CNN) and recurrent neural networks (RNN) with Long Short-Term Memory (LSTM) cells. Differing from previous works that used click-through data with only two classes, Nigam et al [2019] proposed a loss function that differentiates three classes (relevant, partially relevant, and irrelevant) in document search with huge amount of real commercial data.…”

“…We first present the results of using different loss functions in different languages with smooth cosine similarity in Table 2. We compared with three commonly used loss: Mean Square Error(MSE), Proportional Odds Loss (PO) [McCullagh, 1980] and 3P art L2 [Nigam et al, 2019]. The hyperparameter is fixed to 1 for all losses.…”

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Papers

“…Modern e-commerce search engines Nigam et al, 2019) typically consist of a retrieval stage and a ranking stage. The retrieval stage is responsible for collecting a set of relevant products with minimum computational resources.…”