Search Results for author:
Found 17 papers, 3 papers with code
DELPHI: Data for Evaluating LLMs' Performance in Handling Controversial Issues
Controversy is a reflection of our zeitgeist, and an important aspect to any discourse.
Intelligent Assistant Language Understanding On Device
It has recently become feasible to run personal digital assistants on phones and other personal devices.
Feedback Effect in User Interaction with Intelligent Assistants: Delayed Engagement, Adaption and Drop-out
Next, we expand the time horizon to examine behavior changes and show that as users discover the limitations of the IA's understanding and functional capabilities, they learn to adjust the scope and wording of their requests to increase the likelihood of receiving a helpful response from the IA.
Improving Human-Labeled Data through Dynamic Automatic Conflict Resolution
This paper develops and implements a scalable methodology for (a) estimating the noisiness of labels produced by a typical crowdsourcing semantic annotation task, and (b) reducing the resulting error of the labeling process by as much as 20-30% in comparison to other common labeling strategies.
Noise Robust Named Entity Understanding for Voice Assistants
Named Entity Recognition (NER) and Entity Linking (EL) play an essential role in voice assistant interaction, but are challenging due to the special difficulties associated with spoken user queries.
Active Learning for Domain Classification in a Commercial Spoken Personal Assistant
We describe a method for selecting relevant new training data for the LSTM-based domain selection component of our personal assistant system.
NAIL: A General Interactive Fiction Agent
Interactive Fiction (IF) games are complex textual decision making problems.
Learning to Globally Edit Images with Textual Description
The models (bucket, filter bank, and end-to-end) differ in how much expert knowledge is encoded, with the most general version being purely end-to-end.
Demonstration of interactive teaching for end-to-end dialog control with hybrid code networks
This is a demonstration of interactive teaching for practical end-to-end dialog systems driven by a recurrent neural network.
Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning
End-to-end learning of recurrent neural networks (RNNs) is an attractive solution for dialog systems; however, current techniques are data-intensive and require thousands of dialogs to learn simple behaviors.
Sample-efficient Deep Reinforcement Learning for Dialog Control
Representing a dialog policy as a recurrent neural network (RNN) is attractive because it handles partial observability, infers a latent representation of state, and can be optimized with supervised learning (SL) or reinforcement learning (RL).
End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning
This paper presents a model for end-to-end learning of task-oriented dialog systems.
