Search results

A system built on Amazon Translate reduces the workload of human translators.

We present a method to compute the derivative of a learning task with respect to a dataset. A learning task is a function from a training set to the validation error, which can be represented by a trained deep neural network (DNN). The “dataset derivative” is a linear operator, computed around the trained model, that informs how perturbations of the weight of each training sample affect the validation error

Meta-learning learns across historical tasks with the goal to discover a representation from which it is easy to adapt to unseen tasks. Episodic meta-learning attempts to simulate a realistic setting by generating a set of small artificial tasks from a larger set of training tasks for meta-training and proceeds in a similar fashion for meta-testing. However, this (meta-)learning paradigm has recently been

Query-product relevance classification is crucial for e-commerce stores like Amazon, ensuring accurate search results that match customer intent. Using a unified multilingual model across multiple languages/marketplaces tends to yield superior outcomes but also presents challenges, especially in maintaining performance across all languages when the model is updated or expanded to include a new one. To tackle

Recommender systems and search are both indispensable in facilitating personalization and ease of browsing in online fashion platforms. However, the two tools often operate independently, failing to combine the strengths of recommender systems to accurately capture user tastes with search systems’ ability to process user queries. We propose a novel remedy to this problem by automatically recommending personalized

Machine Learning (ML) systems are getting increasingly popular, and drive more and more applications and services in our daily life. This has led to growing concerns over user privacy, since human interaction data typically needs to be transmitted to the cloud in order to train and improve such systems. Federated learning (FL) has recently emerged as a method for training ML models on edge devices using

Contrastive learning has revolutionized the self-supervised image representation learning field and recently been adapted to the video domain. One of the greatest advantages of contrastive learning is that it allows us to flexibly define powerful loss objectives as long as we can find a reasonable way to formulate positive and negative samples to contrast. However, existing approaches rely heavily on the

In product search, negation is frequently used to articulate unwanted product features or components. Modern search engines often struggle to comprehend negations, resulting in suboptimal user experiences. While various methods have been proposed to tackle negations in search, none of them took the vocabulary gap between query keywords and product text into consideration. In this work, we introduced a query

The data on user behaviors is sparse given the vast array of user-item combinations. Attributes related to users (e.g., age), items (e.g., brand), and behaviors (e.g., co-purchase) serve as crucial input sources for item-item transitions of user’s behavior prediction. While recent Transformer-based sequential recommender systems learn the attention matrix for each attribute to update item representations

Bayesian optimization (BO) is a model-based approach for gradient-free black-box function optimization, such as hyperparameter optimization. Typically, BO relies on conventional Gaussian process (GP) regression, whose algorithmic complexity is cubic in the number of evaluations. As a result, GP-based BO cannot leverage large numbers of past function evaluations, for example, to warm-start related BO runs

We devise a coreset selection method based on the idea of gradient matching: the gradients induced by the coreset should match, as closely as possible, those induced by the original training dataset. We evaluate the method in the context of continual learning, where it can be used to curate a rehearsal memory. Our method performs strong competitors such as reservoir sampling across a range of memory sizes

We propose a new method to detect deepfake images using the cue of the source feature inconsistency within the forged images. It is based on the hypothesis that images’ distinct source features can be preserved and extracted after going through state-of-the-art deepfake generation processes. We introduce a novel representation learning approach, called pair-wise self-consistency learning (PCL),for training

Multi-task learning (MTL) considers learning a joint model for multiple tasks by optimizing a convex combination of all task losses. To solve the optimization problem, existing methods use an adaptive weight updating scheme, where task weights are dynamically adjusted based on their respective losses to prioritize difficult tasks. However, these algorithms face a great challenge whenever label noise is

Accurate credit ratings are an essential ingredient in the decision-making process for investors, rating agencies, bond portfolio managers, bankers, and policy makers, as well as an important input for risk management and regulation. Credit ratings are traditionally generated from models that use financial statement data and market data, which are tabular (numeric and categorical). Using machine learning

Crowdsourced machine learning on competition platforms such as Kaggle is a popular and often effective method for generating accurate models. Typically, teams vie for the most accurate model, as measured by overall error on a holdout set, and it is common towards the end of such competitions for teams at the top of the leaderboard to ensemble or average their models outside the platform mechanism to get

Credit ratings are traditionally generated using models that use financial statement data and market data, which is tabular (numeric and categorical). Practitioner and academic models do not include text data. Using an automated approach to combine long-form text from SEC filings with the tabular data, we show how multimodal machine learning using stack ensembling and bagging can generate more accurate

Most recently, there has been significant interest in learning contextual representations for various NLP tasks, by leveraging large scale text corpora to train large neural language models with self-supervised learning objectives, such as Masked Language Model (MLM). However, based on a pilot study, we observe three issues of existing general-purpose language models when they are applied to text-to-SQL

Named Entity Recognition (NER) is a vital task in various NLP applications. However, in many real-world scenarios (e.g., voice-enabled assistants) new named entity types are frequently introduced, entailing re-training NER models to support these new entity types. Re-annotating the original training data for the new entity types could be costly or even impossible when storage limitations or security concerns

Trained on vast corpora of human language, language models demonstrate emergent human-like reasoning abilities. Yet they are still far from true intelligence, which opens up intriguing opportunities to explore the parallels of humans and model behaviors. In this work, we study the ability to skip steps in reasoning—a hallmark of human expertise developed through practice. Unlike humans, who may skip steps

Bayesian optimization (BO) is a sample efficient approach to automatically tune the hyperparameters of machine learning models. In practice, one frequently has to solve similar hyperparameter tuning problems sequentially. For example, one might have to tune a type of neural network learned across a series of different classification problems. Recent work on multi-task BO exploits knowledge gained from previous