In this work, we introduce a bootstrapped, iterative NER model that integrates a PU learning algorithm for recognizing named entities in a low-resource setting. Our approach combines dictionary-based labeling with syntactically-informed label expansion to efficiently enrich the seed dictionaries. Experimental results on a dataset of manually annotated e-commerce product descriptions demonstrate the effectiveness of the proposed framework.

In an attempt to balance precision and recall in the search page, leading digital shops have been effectively nudging users into select category facets as early as in the type-ahead suggestions. In this work, we present SessionPath, a novel neural network model that improves facet suggestions on two counts: first, the model is able to leverage session embeddings to provide scalable personalization; second, SessionPath predicts facets by explicitly producing a probability distribution at each node in the taxonomy path. We benchmark SessionPath on two partnering shops against count-based and neural models, and show how business requirements and model behavior can be combined in a principled way.

Alternative recommender systems are critical for ecommerce companies. They guide customers to explore a massive product catalog and assist customers to find the right products among an overwhelming number of options. However, it is a non-trivial task to recommend alternative products that fit customers’ needs. In this paper, we use both textual product information (e.g. product titles and descriptions) and customer behavior data to recommend alternative products. Our results show that the coverage of alternative products is significantly improved in offline evaluations as well as recall and precision. The final A/B test shows that our algorithm increases the conversion rate by 12% in a statistically significant way. In order to better capture the semantic meaning of product information, we build a Siamese Network with Bidirectional LSTM to learn product embeddings. In order to learn a similarity space that better matches the preference of real customers, we use co-compared data from historical customer behavior as labels to train the network. In addition, we use NMSLIB to accelerate the computationally expensive kNN computation for millions of products so that the alternative recommendation is able to scale across the entire catalog of a major ecommerce site.

Sentiment analysis is crucial for the advancement of artificial intelligence (AI). Sentiment understanding can help AI to replicate human language and discourse. Studying the formation and response of sentiment state from well-trained Customer Service Representatives (CSRs) can help make the interaction between humans and AI more intelligent. In this paper, a sentiment analysis pipeline is first carried out with respect to real-world multi-party conversations - that is, service calls. Based on the acoustic and linguistic features extracted from the source information, a novel aggregated method for voice sentiment recognition framework is built. Each party’s sentiment pattern during the communication is investigated along with the interaction sentiment pattern between all parties.

While buying a product from the e-commerce websites, customers generally have a plethora of questions. From the perspective of both the e-commerce service provider as well as the customers, there must be an effective question answering system to provide immediate answer to the user queries. While certain questions can only be answered after using the product, there are many questions which can be answered from the product specification itself. Our work takes a first step in this direction by finding out the relevant product specifications, that can help answering the user questions. We propose an approach to automatically create a training dataset for this problem. We utilize recently proposed XLNet and BERT architectures for this problem and find that they provide much better performance than the Siamese model, previously applied for this problem. Our model gives a good performance even when trained on one vertical and tested across different verticals.

In this work, we improve the intent classification in an English based e-commerce voice assistant by using inter-utterance context. For increased user adaptation and hence being more profitable, an e-commerce voice assistant is desired to understand the context of a conversation and not have the users repeat it in every utterance. For example, let a user’s first utterance be ‘find apples’. Then, the user may say ‘i want organic only’ to filter out the results generated by an assistant with respect to the first query. So, it is important for the assistant to take into account the context from the user’s first utterance to understand her intention in the second one. In this paper, we present our approach for contextual intent classification in Walmart’s e-commerce voice assistant. It uses the intent of the previous user utterance to predict the intent of her current utterance. With the help of experiments performed on real user queries we show that our approach improves the intent classification in the assistant.

In this paper, we present a semi-supervised bootstrapping approach to detect product or service related complaints in social media. Our approach begins with a small collection of annotated samples which are used to identify a preliminary set of linguistic indicators pertinent to complaints. These indicators are then used to expand the dataset. The expanded dataset is again used to extract more indicators. This process is applied for several iterations until we can no longer find any new indicators. We evaluated this approach on a Twitter corpus specifically to detect complaints about transportation services. We started with an annotated set of 326 samples of transportation complaints, and after four iterations of the approach, we collected 2,840 indicators and over 3,700 tweets. We annotated a random sample of 700 tweets from the final dataset and observed that nearly half the samples were actual transportation complaints. Lastly, we also studied how different features based on semantics, orthographic properties, and sentiment contribute towards the prediction of complaints.

In e-commerce, recommender systems have become an indispensable part of helping users explore the available inventory. In this work, we present a novel approach for item-based collaborative filtering, by leveraging BERT to understand items, and score relevancy between different items. Our proposed method could address problems that plague traditional recommender systems such as cold start, and “more of the same” recommended content. We conducted experiments on a large-scale real-world dataset with full cold-start scenario, and the proposed approach significantly outperforms the popular Bi-LSTM model.

Product reviews are a huge source of natural language data in e-commerce applications. Several millions of customers write reviews regarding a variety of topics. We categorize these topics into two groups as either “category-specific” topics or as “generic” topics that span multiple product categories. While we can use a supervised learning approach to tag review text for generic topics, it is impossible to use supervised approaches to tag category-specific topics due to the sheer number of possible topics for each category. In this paper, we present an approach to tag each review with several product category-specific tags on Indonesian language product reviews using a semi-supervised approach. We show that our proposed method can work at scale on real product reviews at Tokopedia, a major e-commerce platform in Indonesia. Manual evaluation shows that the proposed method can efficiently generate category-specific product tags.

In e-commerce system, category prediction is to automatically predict categories of given texts. Different from traditional classification where there are no relations between classes, category prediction is reckoned as a standard hierarchical classification problem since categories are usually organized as a hierarchical tree. In this paper, we address hierarchical category prediction. We propose a Deep Hierarchical Classification framework, which incorporates the multi-scale hierarchical information in neural networks and introduces a representation sharing strategy according to the category tree. We also define a novel combined loss function to punish hierarchical prediction losses. The evaluation shows that the proposed approach outperforms existing approaches in accuracy.

In recent years, there has been an increase in online shopping resulting in an increased number of online reviews. Customers cannot delve into the huge amount of data when they are looking for specific aspects of a product. Some of these aspects can be extracted from the product reviews. In this paper we introduced SimsterQ - a clustering based system for answering questions that makes use of word vectors. Clustering was performed using cosine similarity scores between sentence vectors of reviews and questions. Two variants (Sim and Median) with and without stopwords were evaluated against traditional methods that use term frequency. We also used an n-gram approach to study the effect of noise. We used the reviews in the Amazon Reviews dataset to pick the answers. Evaluation was performed both at the individual sentence level using the top sentence from Okapi BM25 as the gold standard and at the whole answer level using review snippets as the gold standard. At the sentence level our system performed slightly better than a more complicated deep learning method. Our system returned answers similar to the review snippets from the Amazon QA Dataset as measured by the cosine similarity. Analysis was also performed on the quality of the clusters generated by our system.

In recent years, the focus of e-Commerce research has been on better understanding the relationship between the internet marketplace, customers, and goods and services. This has been done by examining information that can be gleaned from consumer information, recommender systems, click rates, or the way purchasers go about making buying decisions, for example. This paper takes a very different approach and examines the companies themselves. In the past ten years, e-Commerce giants such as Amazon, Skymall, Wayfair, and Groupon have been embroiled in class action security lawsuits promulgated under Rule 10b(5), which, in short, is one of the Securities and Exchange Commission’s main rules surrounding fraud. Lawsuits are extremely expensive to the company and can damage a company’s brand extensively, with the shareholders left to suffer the consequences. We examined the Management Discussion and Analysis and the Market Risks for 96 companies using sentiment analysis on selected financial measures and found that we were able to predict the outcome of the lawsuits in our dataset using sentiment (tone) alone to a recall of 0.8207 using the Random Forest classifier. We believe that this is an important contribution as it has cross-domain implications and potential, and opens up new areas of research in e-Commerce, finance, and law, as the settlements from the class action lawsuits in our dataset alone are in excess of $1.6 billion dollars, in aggregate.

In this paper, we study the applicability of Bayesian Parametric and Non-parametric methods for user clustering in an E-commerce search setting. To the best of our knowledge, this is the first work that presents a comparative study of various Bayesian clustering methods in the context of product search. Specifically, we cluster users based on their topical patterns from their respective product search queries. To evaluate the quality of the clusters formed, we perform a collaborative query recommendation task. Our findings indicate that simple parametric model like Latent Dirichlet Allocation (LDA) outperforms more sophisticated non-parametric methods like Distance Dependent Chinese Restaurant Process and Dirichlet Process-based clustering in both tasks.