Search results

Customers interacting with product search en-gines are increasingly formulating information-seeking queries. Frequently Asked Ques-tion (FAQ) retrieval aims to retrieve common question-answer pairs for a user query with question intent. Integrating FAQ retrieval in product search can not only empower users to make more informed purchase decisions, but also enhance user retention through efficient post-purchase

As fraudulent and abusive activities performed by groups continue to plague e-commerce stores, we realize that detecting groups of abusers, or Ring-of-Abusers (RoAs), has become crucial. Unlike existing works about abuser detection on e-commerce stores that merely consider the individual features of abusers or the relationships among abusers, we design a Universal Ring-Of-Abusers Detection framework (abbreviated

The success of self-supervised learning in computer vision and natural language processing has motivated pretraining methods on tabular data. However, most existing tabular self-supervised learning models fail to leverage information across multiple data tables and cannot generalize to new tables. In this work, we introduce XTab, a framework for cross-table pretraining of tabular transformers on datasets

Despite the emergence of principled methods for domain adaptation under label shift, their sensitivity to shifts in class conditional distributions is precariously under explored. Meanwhile, popular deep domain adaptation heuristics tend to falter when faced with label proportions shifts. While several papers modify these heuristics in attempts to handle label proportions shifts, inconsistencies in evaluation

Customers who reach out for customer service support may face a range of issues that vary in complexity. Routing high-complexity contacts to junior agents can lead to multiple transfers or repeated contacts, while directing low-complexity contacts to senior agents can strain their capacity to assist customers who need professional help. To tackle this, a machine learning model that accurately predicts the

E-commerce companies deal with a high volume of customer service requests daily. While a simple annotation system is often used to summarize the topics of customer contacts, thoroughly exploring each specific issue can be challenging. This presents a critical concern, especially during an emerging outbreak where companies must quickly identify and address specific issues. To tackle this challenge, we propose

Customer service is often the most time-consuming aspect for e-commerce websites, with each contact typically taking 10-15 minutes. Effectively routing customers to appropriate agents without transfers is therefore crucial for e-commerce success. To this end, we have developed a machine learning framework that predicts the complexity of customer contacts and routes them to appropriate agents accordingly

We investigate semi-structured document classification in a zero-shot setting. Classification of semi-structured documents is more challenging than that of standard unstructured documents, as positional, layout, and style information play a vital role in interpreting such documents. The standard classification setting where categories are fixed during both training and testing falls short in dynamic environments

Encoder-decoder deep neural networks have been increasingly studied for multi-horizon time series forecasting, especially in real-world applications. However, to forecast accurately, these sophisticated neural forecasters typically rely on a large number of time series examples with substantial history. A rapidly growing topic of interest is forecasting time series which lack sufficient historical data—often

Reliable storage systems must be crash consistent – guaranteed to recover to a consistent state after a crash. Crash consistency is non-trivial as it requires maintaining complex invariants about persistent data structures in the presence of caching, reordering, and system failures. Current programming models offer little support for implementing crash consistency, forcing storage system developers to roll

Ensembles have long been a cornerstone in improving performance by integrating black-box base learners. The primary approach, “stacked generalization” is inherently static, lacking adaptability to changes in input data post-training. This limitation is more pronounced in time series forecasting, where these methods struggle to manage temporal correlations or non-stationarity. Given base learners may perform

In this work, we show how to collect and use human feedback to improve complex models in information retrieval systems. Human feedback often improves model performance, yet little has been shown to combine human feedback and model tuning in an end-to-end setup with public resources. To this end, we develop a system called Crowd-Coachable Retriever (CCR),1 where we use crowd-sourced workers and open-source

Predictive maintenance (PdM) is one of the most important machine learning (ML) use cases in a wide range of businesses that own or manufacture machinery. Many PdM applications utilize event logs/sequences that record machine operating conditions and health data. However, industrial scale PdM use cases bring a variety of challenges which makes it difficult to directly apply state-of-the-art models. In this

Rogue actors employ sophisticated automation techniques to mimic human browsing/click patterns and generate invalid (i.e., fraudulent or robotic) traffic on retail marketplaces to artificially inflate their key performance metrics at the expense of their legitimate competitors. To maintain a clean and fair advertising system, it is essential to identify and mitigate ad traffic that is invalid, i.e., fraudulent

SDE, TQ for SSPA

Subledgers maintain detailed information about specific accounts or transactions in order to substantiate the general ledger. Subledgers provide a granular level of detail for financial reporting and analysis, which is especially essential for accounts receivables and payables. The size of subledgers can vary greatly depending on the complexity and volume of transactions and their size can also increase

In large corporations, millions of cash transactions are booked via cash management software (CMS) per month. Most CMS systems adopt a key-word (search string) based matching logic for booking, which checks if the cash transaction description contains a specific search string and books the transaction to an appropriate general ledger account (GL-account) according to a booking rule. However, due to the

Software Development Manager

In this work, we introduce a diffusion-based text-to-speech (TTS) system for accent modelling. TTS systems have become a natural part of our surroundings. Nevertheless, because of the complexity of accent modelling, recent state-of-the-art solutions mainly focus on the most common variants of each language. In this work, we propose to address this issue with a newly proposed diffusion generative model (

Multilingual information retrieval (IR) is challenging since annotated training data is costly to obtain in many languages. We present an effective method to train multilingual IR systems when only English IR training data and some parallel corpora between English and other languages are available. We leverage parallel and non-parallel corpora to improve the pretrained multilingual language models’ cross-lingual