Search results

We introduce and describe the results of a novel shared task on bandit learning for machine translation. The task was organized jointly by Amazon and Heidelberg University for the first time at the Second Conference on Machine Translation (WMT 2017). The goal of the task is to encourage research on learning machine translation from weak user feedback instead of human references or post-edits. On each of

Topics generated by topic models are usually represented by lists of t terms or alternatively using short phrases or images. The current state-of-the-art work on labeling topics using images selects images by re-ranking a small set of candidates for a given topic. In this paper, we present a more generic method that can estimate the degree of association between any arbitrary pair of an unseen topic and

Bayesian optimization has been successfully used to optimize complex black-box functions whose evaluations are expensive. In many applications, like in deep learning and predictive analytics, the optimization domain is itself complex and structured. In this work, we focus on use cases where this domain exhibits a known dependency structure. The benefit of leveraging this structure is twofold: we explore

Estimating the relevance of documents based on the user feedback is an essential component of search, retrieval and ranking problems. User click modeling in search has focused primarily on factoring out the position bias. It is easy to see that the query type (generic queries vs specific queries) and user intent (purchase vs exploration) also introduce a bias in the click signal. In other words, the results

The Moore-Lewis method of “intelligent selection of language model training data” is very effective, cheap, efficient... and also has structural problems. (1) The method defines relevance by playing language models trained on the in-domain and the out-of-domain (or data pool) corpora against each other. This powerful idea – which we set out to preserve – treats the two corpora as the opposing ends of a

Rapidly growing product lines and services require a finer-granularity forecast that considers geographic locales. However the open question remains, how to assess the quality of a spatio-temporal forecast?

We present a platform built on large-scale, data-centric machine learning (ML) approaches, whose particular focus is demand forecasting in retail. At its core, this platform enables the training and application of probabilistic demand forecasting models, and provides convenient abstractions and support functionality for forecasting problems. The platform comprises of a complex end-to-end machine learning

We describe SOCKEYE, 1 an open-source sequence-to-sequence toolkit for Neural Machine Translation (NMT). SOCKEYE is a production-ready framework for training and applying models as well as an experimental platform for researchers. Written in Python and built on MXNET, the toolkit offers scalable training and inference for the three most prominent encoder-decoder architectures: attentional recurrent neural

Sockeye is an open-source sequence-to-sequence framework for neural machine translation (NMT) built on PyTorch. It implements distributed training and optimized inference for state-of-the-art models, powering Amazon Translate and other MT applications. Recent developments and changes are tracked in our CHANGELOG. For a quickstart guide to training a standard NMT model on any size of data, see the WMT 2014

You can build smart home and other products that customers can control from millions of Alexa devices with just their voice. Expand your device’s capabilities with Alexa to create delightful experiences for lights, switches, thermostats, cameras, locks, and more. Plus, your Alexa-connected devices continue to become smarter with Alexa’s growing list of smart home capabilities and features that leverage

Meet the Mila team from the University of Montreal, a French-language public research university in Montreal, Quebec, Canada.

Picture walking into your house after a long day. As you step in, your favorite music starts playing in the background and the lights dim to suit the weather outside.

Meet the SluBot team from UC Santa Cruz, a public land-grant research university in Santa Cruz, California.

We're an eclectic team of research-oriented undergraduate and graduate students in Princeton's CS and math departments.

Sounding Board is a conversational agent that engages users through thoughtful and informative discussion.

Meet the EmersonBot team from Emory University, a private research university in Atlanta, Georgia, US.

The UC Berkeley team consists of William, Phillip, Piyush, and James, and is the only fully undergraduate team in the competition.

This team, consisting of PhD and Masters students from Carnegie Mellon University, brings together experience in chatbot interaction strategies, question answering, neural modeling and machine learning.

We are the Alquist team from CTU, Prague, Czech Republic.

We are Edina, from the University of Edinburgh, a world-leading institution in Artificial Intelligence.