Search results

New AI model enables iterative refinement of results and better color matching.

Machine learning systems often act on “features” extracted from input data. In a natural-language-understanding system, for instance, the features might include words’ parts of speech, as assessed by an automatic syntactic parser, or whether a sentence is in the active or passive voice.

Recent work has achieved great success in utilizing global contextual information for semantic segmentation, including increasing the receptive field and aggregating pyramid feature representations. In this paper, we go beyond global context and explore the fine grained representation using co-occurrent features by introducing Co-occurrent Feature Model, which predicts the distribution of co-occurrent features

Logo recognition is the task of identifying and classifying logos. Logo recognition is a challenging problem as there is no clear definition of a logo and there are huge variations of logos, brands and re-training to cover every variation is impractical. In this paper, we formulate logo recognition as a few-shot object detection problem. The two main components in our pipeline are universal logo detector

Last year, Amazon announced the beta release of Alexa Guard, a new service that lets customers who are leaving the house instruct their Echo devices to listen for glass breaking or smoke and carbon dioxide alarms going off. At this year’s International Conference on Acoustics, Speech, and Signal Processing, our team is presenting several papers on sound detection. I wrote about one of them a few weeks ago, a new method for doing machine learning with unbalanced data sets.

A knowledge graph (e.g., Freebase, YAGO) is a multi-relational graph representing rich factual information among entities of various types. Entity alignment is the key step towards knowledge graph integration from multiple sources. It aims to identify entities across different knowledge graphs that refer to the same real-world entity. However, current entity alignment systems overlook the sparsity of different

In the past few weeks, Amazon announced versions of Alexa in three new languages: Hindi, U.S. Spanish, and Brazilian Portuguese. Like all new-language launches, these addressed the problem of how to bootstrap the machine learning models that interpret customer requests, without the ability to learn from customer interactions.

Many businesses and consumers are extending the capabilities of voice-based services such as Amazon Alexa, Google Home, Microsoft Cortana, and Apple Siri to create custom voice experiences (also known as skills). As the number of these experiences increases, a key problem is the discovery of skills that can be used to address a user’s request. In this paper, we focus on conversational skill discovery and

Extreme multi-label text classification (XMC) concerns tagging input text with the most relevant labels from an extremely large set. Recently, pretrained language representation models such as BERT (Bidirectional Encoder Representations from Transformers) have been shown to achieve outstanding performance on many NLP tasks including sentence classification with small label sets (typically fewer than thousands

Understanding the principles of causal inference in the visual system has a long history at least since the seminal studies by Albert Michotte. Many cognitive and machine learning scientists believe that intelligent behavior requires agents to possess causal models of the world. Recent ML algorithms exploit the dependence structure of additive noise terms for inferring causal structures from observational

Communication bottleneck has been identified as a significant issue in distributed optimization of large-scale learning models. Recently, several approaches to mitigate this problem have been proposed, including different forms of gradient compression or computing local models and mixing them iteratively. In this paper, we propose Qsparse-local-SGD algorithm, which combines aggressive sparsification with

Recent works on end-to-end trainable neural network based approaches have demonstrated state-of-the-art results on dialogue state tracking. The best performing approaches estimate a probability distribution over all possible slot values. However, these approaches do not scale for large value sets commonly present in real-life applications and are not ideal for tracking slot values that were not observed

Studies on emotion recognition(ER) show that combining lexical and acoustic information results in more robust and accurate models. The majority of the studies focus on settings where both modalities are available in training and evaluation. However, in practice, this is not always the case; getting ASR output may represent a bottleneck in a deployment pipeline due to computational complexity or privacy

Recent advances in deep learning greatly boost the performance of object detection. State-of-the-art methods such as Faster-RCNN, FPN and R-FCN have achieved high accuracy in challenging benchmark datasets. However, these methods require fully annotated object bounding boxes for training, which are incredibly hard to scale up due to the high annotation cost. Weakly-supervised methods, on the other hand,

Every day, tens of thousands of Amazon customers message Amazon’s selling partners inquiring about orders, products and services. Unfortunately, we have observed over time that buyers may send unsolicited and often times mal intended messages to sellers through the buyer-seller messaging (BSM) service. Although the BSM service gives the ability to sellers to report such messages, most of them do not make

On-policy reinforcement learning (RL) algorithms have high sample complexity while offpolicy algorithms are difficult to tune. Merging the two holds the promise to develop efficient algorithms that generalize across diverse environments. It is however challenging in practice to find suitable hyper-parameters that govern this trade off. This paper develops a simple algorithm named P3O that interleaves offpolicy

An automated metric to evaluate dialogue quality is vital for optimizing data driven dialogue management. The common approach of relying on explicit user feedback during a conversation is intrusive and sparse. Current models to estimate user satisfaction use limited feature sets and employ annotation schemes with limited generalizability to conversations spanning multiple domains. To address these gaps,

I argue that regularizing terms in standard regression methods not only help against overfitting finite data, but sometimes also yield better causal models in the infinite sample regime. I first consider a multi-dimensional variable linearly influencing a target variable with some multi-dimensional unobserved common cause, where the confounding effect can be decreased by keep-ing the penalizing term in

Many forms of interaction between computer systems and users are recorded in the form of event records, such as login events, API call records, bank transaction records, etc. These records are often comprised of high-dimensional categorical variables, such as user name, zip code, autonomous system number, etc. In this work, we consider anomaly detection for such data sets, where each record consists of

The task of Natural Language Inference (NLI) is widely modeled as supervised sentence pair classification. While there has been a lot of work recently on generating explanations of the predictions of classifiers on a single piece of text, there have been no attempts to generate explanations of classifiers operating on pairs of sentences. In this paper, we show that it is possible to generate token-level