Search results

Gunrock 2.0 is built on top of Gunrock with an emphasis on user adaptation. Gunrock 2.0 combines various neural natural language understanding modules, including named entity detection, linking, and dialog act prediction, to improve user understanding. Its dialog management is a hierarchical model that handles various topics, such as movies, music, and sports. The system-level dialog manager can handle

This report describes Athena, a dialogue system for spoken conversation on popular topics and current events. We develop a flexible topic-agnostic approach to dialogue management that dynamically configures dialogue based on general principles of entity and topic coherence. Athena’s dialogue manager uses a contract-based method where discourse constraints are dispatched to clusters of response generators

Tartan is a social bot that engages users in sharing daily personal experiences in multiple domains. Our work contributes to Conversational AI in two aspects: 1) We extract common-sense knowledge expressed in large-scale user utterances in conversations, and find that more than 20% of the shared information is related to personal life, such as social relationships and individual activities. 2) Based on

Building a dialogue system able to talk fluently and meaningfully in an open domain conversation is one of the foundational challenges in the field of AI. Recent progress in NLP driven by the application of the deep neural networks and large language models opened new possibilities to solve many hard problems of the conversational AI. Alexa Prize Socialbot Grand Challenge gives a unique opportunity to test

We propose Bernard: a framework for an engaging open-domain socialbot. While the task of open-domain dialog generation remains a difficult one, we explore various strategies to generate coherent dialog given an arbitrary dialog history. We incorporate a stateful autonomous dialog manager using non-deterministic finite automata to control multi-turn conversations. We show that powerful pretrained language

We describe the ZOTBOT system for open-ended conversations, designed for the Alexa Prize competition. We focus on two main shortcomings in existing conversational agents: lack of awareness in commonsense reasoning when responding to user utterances (resulting in nonsensical or uninteresting responses) and inability to understand semantics and converse naturally about fact-based articles in a compelling

Conversational Intelligence requires that a person engage on informational, personal and relational levels. Advances in Natural Language Understanding have helped recent chatbots succeed at dialog on the informational level. However, current techniques still lag for conversing with humans on a personal level and fully relating to them. The University of Michigan’s submission to the Alexa Prize Grand Challenge

Kernel methods are popular and effective techniques for learning on structured data, such as trees and graphs. One of their major drawbacks is the computational cost related to making a prediction on an example, which manifests in the classification phase for batch kernel methods, and especially in online learning algorithms. In this paper, we analyze how to speed up the prediction when the kernel function

The building block of Transformer can be seen as inducing message passing over a complete graph whose nodes correspond to input tokens. Such dense connections make the Transformer data-hungry. Star-Transformer exploits short-term dependencies more heavily by keeping the connections between adjacent tokens but relaying long dependencies via a central node, thereby reducing the number of connections from

In this paper we address the problem of detecting previously unseen novel audio events in the presence of real-life acoustic backgrounds. Specifically, during training, we learn subspaces corresponding to each acoustic background, and during testing the audio frame in question is decomposed into a component that lies on the mixture of subspaces and a super gaussian outlier component.Based on the energy

We examine the impact of "big data" on firm performance in the context of forecast accuracy using proprietary retail sales data obtained from Amazon. We measure the accuracy of forecasts in two relevant dimensions: the number of products (N), and the number of time periods for which a product is available for sale (T). Theory suggests diminishing returns to larger N and T, with relative forecast errors

In this paper, we introduce an Augmented Lagrangian based method in a search relevance ranking algorithm to incorporate the multi-dimensional nature of relevance and business constraints, both of which are the requirements for building relevance ranking models in production. The off-the-shelf solutions cannot handle such complex objectives and therefore, modelers are left hand-tuning of parameters that

Building open domain conversational systems that allow users to have engaging conversations on topics of their choice is a challenging task. The Alexa Prize Socialbot Grand Challenge was launched in 2016 to tackle the problem of achieving natural, sustained, coherent and engaging open-domain dialogs. In the third iteration of the competition, university teams have moved the needle on the state of the art

A person’s tone of voice can tell you a lot about how they’re feeling. Not surprisingly, emotion recognition is an increasingly popular conversational-AI research topic.

Text normalization is an important process in conversational AI. If an Alexa customer says, “book me a table at 5:00 p.m.”, the automatic speech recognizer will transcribe the time as “five p m”. Before a skill can handle this request, “five p m” will need to be converted to “5:00PM”. Once Alexa has processed the request, it needs to synthesize the response — say, “Is 6:30 p.m. okay?” Here, 6:30PM will be converted to “six thirty p m” for the text-to-speech synthesizer. We call the process of converting “5:00PM” to “five p m” text normalization and its counterpart — converting “five p m” to “5:00PM” — inverse text normalization.

Recently, we published a paper showing that training a neural network to do language processing in English, then retraining it in German, drastically reduces the amount of German-language training data required to achieve a given level of performance.

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

Traditionally, Alexa has interpreted customer requests according to their intents and slots. If you say, “Alexa, play ‘What’s Going On?’ by Marvin Gaye,” the intent should be PlayMusic, and “‘What’s Going On?’” and “Marvin Gaye” should fill the slots SongName and ArtistName.

When a customer asks Alexa to play “Hey Jude”, and Alexa responds, “Playing 'Hey Jude' by the Beatles,” that response is generated by a text-to-speech (TTS) system, which converts textual inputs into synthetic-speech outputs...

One of the ways that we’re always trying to improve Alexa’s performance is by teaching her to ignore speech that isn’t intended for her. At this year’s International Conference on Acoustics, Speech, and Signal Processing, my colleagues and I will present a new technique for doing this, which could complement the techniques that Alexa already uses.