Search results

Our scientific approach focuses on developing novel models for neural natural language generation and dialogue management.

The team envisions a future where personal, sensible social conversational agents focus on conversational diversity and consistency in personalized dialogue.

Developing machine learning frameworks that can enhance context-aware AI has been an area of focus for Dhillon’s entire career.

Consider a standard recommendation/retrieval problem where given a query, the goal is to retrieve the most relevant items. Inductive matrix completion (IMC) method is a standard approach for this problem where the given query as well as the items are embedded in a common low-dimensional space. The inner product between a query embedding and an item embedding reflects relevance of the (query, item) pair.

Multimedia streaming services over spoken dialog systems have become ubiquitous. User-entity affinity modeling is critical for the system to understand and disambiguate user intents and personalize user experiences. However, fully voice-based interaction demands quantification of novel behavioral cues to determine user affinities. In this work, we propose using play duration cues to learn a matrix factorization

Using cosine similarity rather than dot product to compare vectors helps prevent "catastrophic forgetting".

Howard University is the first Black college to host the American Economic Association Summer Training and Scholarship Program.

To ensure that Alexa Prize contestants can concentrate on dialogue systems — the core technology of socialbots — Amazon scientists and engineers built a set of machine learning modules that handle fundamental conversational tasks and a development environment that lets contestants easily mix and match existing modules with those of their own design.

In this paper we investigate a time delay neural network (TDNN) for a keyword spotting task that requires low CPU, memory and latency. The TDNN is trained with transfer learning and multi-task learning. Temporal subsampling enabled by the time delay architecture reduces computational complexity. We propose to apply singular value decomposition (SVD) to further reduce TDNN complexity. This allows us to first

We are EVE, a team of researchers from the Brigham Young University Perception, Control, and Cognition Laboratory, and we've been accepted to the Amazon Alexa Prize Challenge.

As open-ended human-chatbot interaction becomes commonplace, sensitive content detection gains importance. In this work, we propose a two stage semi-supervised approach to bootstrap large-scale data for automatic sensitive language detection from publicly available web resources. We explore various data selection methods including 1) using a blacklist to rank online discussion forums by the level of their

Large scale Natural Language Understanding (NLU) systems are typically trained on large quantities of data, requiring a fast and scalable training strategy. A typical design for NLU systems consists of domain-level NLU modules (domain classifier, intent classifier and named entity recognizer). Hypotheses (NLU interpretations consisting of various intent+slot combinations) from these domain specific modules

We describe our Alexa prize system (called ‘Alana’) which consists of an ensemble of bots, combining rule-based and machine learning systems, and using a contextual ranking mechanism to choose system responses. This paper reports on the version of the system developed and evaluated in the semi-finals of the competition (i.e. up to 15 August 2017), but not on subsequent enhancements. The ranker for this

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

In this paper, we propose novel gossip algorithms for the low-rank decentralized matrix completion problem. The proposed approach is on the Riemannian Grassmann manifold that allows local matrix completion by different agents while achieving asymptotic consensus on the global low-rank factors. The resulting approach is scalable and parallelizable. Our numerical experiments show the good performance of the

We describe IrisBot, a conversational agent that aims to help a customer be informed about the world around them, while being entertained and engaged. Our bot attempts to incorporate real-time search, informed advice, and latest news recommendation into a coherent conversation. IrisBot can already track information on the latest topics and opinions from News, Sports, and Entertainment and some specialized

We present a zero-shot learning approach for text classification, predicting which natural language understanding domain can handle a given utterance. Our approach can predict domains at runtime that did not exist at training time. We achieve this extensibility by learning to project utterances and domains into the same embedding space while generating each domain-specific embedding from a set of attributes

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

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

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