Query Rewriting via Cycle-Consistent Translation for E-Commerce Search

Nowadays e-commerce search has become an integral part of many people's shopping routines. One critical challenge in today's e-commerce search is the semantic matching problem where the relevant items may not contain the exact terms in the user query. In this paper, we propose a novel deep neural network based approach to query rewriting, in order to tackle this problem. Specifically, we formulate query rewriting into a cyclic machine translation problem to leverage abundant click log data. Then we introduce a novel cyclic consistent training algorithm in conjunction with state-of-the-art machine translation models to achieve the optimal performance in terms of query rewriting accuracy. In order to make it practical in industrial scenarios, we optimize the syntax tree construction to reduce computational cost and online serving latency. Offline experiments show that the proposed method is able to rewrite hard user queries into more standard queries that are more appropriate for the inverted index to retrieve. Comparing with human curated rule-based method, the proposed model significantly improves query rewriting diversity while maintaining good relevancy. Online A/B experiments show that it improves core e-commerce business metrics significantly. Since the summer of 2020, the proposed model has been launched into our search engine production, serving hundreds of millions of users.

BERT2DNN: BERT Distillation with Massive Unlabeled Data for Online E-Commerce Search

Relevance has significant impact on user experience and business profit for e-commerce search platform. In this work, we propose a data-driven framework for search relevance prediction, by distilling knowledge from BERT and related multi-layer Transformer teacher models into simple feed-forward networks with large amount of unlabeled data. The distillation process produces a student model that recovers more than 97\% test accuracy of teacher models on new queries, at a serving cost that's several magnitude lower (latency 150x lower than BERT-Base and 15x lower than the most efficient BERT variant, TinyBERT). The applications of temperature rescaling and teacher model stacking further boost model accuracy, without increasing the student model complexity. We present experimental results on both in-house e-commerce search relevance data as well as a public data set on sentiment analysis from the GLUE benchmark. The latter takes advantage of another related public data set of much larger scale, while disregarding its potentially noisy labels. Embedding analysis and case study on the in-house data further highlight the strength of the resulting model. By making the data processing and model training source code public, we hope the techniques presented here can help reduce energy consumption of the state of the art Transformer models and also level the playing field for small organizations lacking access to cutting edge machine learning hardwares.

A Survey of Deep Active Learning

Active learning (AL) attempts to maximize the performance gain of the model by marking the fewest samples. Deep learning (DL) is greedy for data and requires a large amount of data supply to optimize massive parameters, so that the model learns how to extract high-quality features. In recent years, due to the rapid development of internet technology, we are in an era of information torrents and we have massive amounts of data. In this way, DL has aroused strong interest of researchers and has been rapidly developed. Compared with DL, researchers have relatively low interest in AL. This is mainly because before the rise of DL, traditional machine learning requires relatively few labeled samples. Therefore, early AL is difficult to reflect the value it deserves. Although DL has made breakthroughs in various fields, most of this success is due to the publicity of the large number of existing annotation datasets. However, the acquisition of a large number of high-quality annotated datasets consumes a lot of manpower, which is not allowed in some fields that require high expertise, especially in the fields of speech recognition, information extraction, medical images, etc. Therefore, AL has gradually received due attention. A natural idea is whether AL can be used to reduce the cost of sample annotations, while retaining the powerful learning capabilities of DL. Therefore, deep active learning (DAL) has emerged. Although the related research has been quite abundant, it lacks a comprehensive survey of DAL. This article is to fill this gap, we provide a formal classification method for the existing work, and a comprehensive and systematic overview. In addition, we also analyzed and summarized the development of DAL from the perspective of application. Finally, we discussed the confusion and problems in DAL, and gave some possible development directions for DAL.

Fine-tune BERT for E-commerce Non-Default Search Ranking

The quality of non-default ranking on e-commerce platforms, such as based on ascending item price or descending historical sales volume, often suffers from acute relevance problems, since the irrelevant items are much easier to be exposed at the top of the ranking results. In this work, we propose a two-stage ranking scheme, which first recalls wide range of candidate items through refined query/title keyword matching, and then classifies the recalled items using BERT-Large fine-tuned on human label data. We also implemented parallel prediction on multiple GPU hosts and a C++ tokenization custom op of Tensorflow. In this data challenge, our model won the 1st place in the supervised phase (based on overall F1 score) and 2nd place in the final phase (based on average per query F1 score).

Adversarial Mixture Of Experts with Category Hierarchy Soft Constraint

Product search is the most common way for people to satisfy their shopping needs on e-commerce websites. Products are typically annotated with one of several broad categorical tags, such as "Clothing" or "Electronics", as well as finer-grained categories like "Refrigerator" or "TV", both under "Electronics". These tags are used to construct a hierarchy of query categories. Feature distributions such as price and brand popularity vary wildly across query categories. In addition, feature importance for the purpose of CTR/CVR predictions differs from one category to another. In this work, we leverage the Mixture of Expert (MoE) framework to learn a ranking model that specializes for each query category. In particular, our gate network relies solely on the category ids extracted from the user query. While classical MoE's pick expert towers spontaneously for each input example, we explore two techniques to establish more explicit and transparent connections between the experts and query categories. To help differentiate experts on their domain specialties, we introduce a form of adversarial regularization among the expert outputs, forcing them to disagree with one another. As a result, they tend to approach each prediction problem from different angles, rather than copying one another. This is validated by a much stronger clustering effect of the gate output vectors under different categories. In addition, soft gating constraints based on the categorical hierarchy are imposed to help similar products choose similar gate values. and make them more likely to share similar experts. This allows aggregation of training data among smaller sibling categories to overcome data scarcity issues among the latter. Experiments on a learning-to-rank dataset gathered from a leading e-commerce search log demonstrate that MoE with our improvements consistently outperforms competing models.

A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions

Deep learning has made major breakthroughs and progress in many fields. This is due to the powerful automatic representation capabilities of deep learning. It has been proved that the design of the network architecture is crucial to the feature representation of data and the final performance. In order to obtain a good feature representation of data, the researchers designed various complex network architectures. However, the design of the network architecture relies heavily on the researchers' prior knowledge and experience. Therefore, a natural idea is to reduce human intervention as much as possible and let the algorithm automatically design the architecture of the network. Thus going further to the strong intelligence. In recent years, a large number of related algorithms for \textit{Neural Architecture Search} (NAS) have emerged. They have made various improvements to the NAS algorithm, and the related research work is complicated and rich. In order to reduce the difficulty for beginners to conduct NAS-related research, a comprehensive and systematic survey on the NAS is essential. Previously related surveys began to classify existing work mainly from the basic components of NAS: search space, search strategy and evaluation strategy. This classification method is more intuitive, but it is difficult for readers to grasp the challenges and the landmark work in the middle. Therefore, in this survey, we provide a new perspective: starting with an overview of the characteristics of the earliest NAS algorithms, summarizing the problems in these early NAS algorithms, and then giving solutions for subsequent related research work. In addition, we conducted a detailed and comprehensive analysis, comparison and summary of these works. Finally, we give possible future research directions.

Saliency Detection via Bidirectional Absorbing Markov Chain

Traditional saliency detection via Markov chain only considers boundaries nodes. However, in addition to boundaries cues, background prior and foreground prior cues play a complementary role to enhance saliency detection. In this paper, we propose an absorbing Markov chain based saliency detection method considering both boundary information and foreground prior cues. The proposed approach combines both boundaries and foreground prior cues through bidirectional Markov chain. Specifically, the image is first segmented into superpixels and four boundaries nodes (duplicated as virtual nodes) are selected. Subsequently, the absorption time upon transition node's random walk to the absorbing state is calculated to obtain foreground possibility. Simultaneously, foreground prior as the virtual absorbing nodes is used to calculate the absorption time and obtain the background possibility. Finally, two obtained results are fused to obtain the combined saliency map using cost function for further optimization at multi-scale. Experimental results demonstrate the outperformance of our proposed model on 4 benchmark datasets as compared to 17 state-of-the-art methods.