Search Results for author:
Found 19 papers, 6 papers with code
TOAD: Task-Oriented Automatic Dialogs with Diverse Response Styles
In light of recent advances in large language models (LLMs), the expectations for the next generation of virtual assistants include enhanced naturalness and adaptability across diverse usage scenarios.
Languages You Know Influence Those You Learn: Impact of Language Characteristics on Multi-Lingual Text-to-Text Transfer
For a given language, we are able to predict zero-shot performance, that increases on a logarithmic scale with the number of few-shot target language data points.
Prompting for a conversation: How to control a dialog model?
Dialog modelling faces a difficult trade-off.
Plan-then-Generate: Controlled Data-to-Text Generation via Planning
However, the lack of ability of neural models to control the structure of generated output can be limiting in certain real-world applications.
Non-Autoregressive Text Generation with Pre-trained Language Models
In this work, we show that BERT can be employed as the backbone of a NAG model to greatly improve performance.
A Generative Model for Joint Natural Language Understanding and Generation
This approach allows us to explore both spaces of natural language and formal representations, and facilitates information sharing through the latent space to eventually benefit NLU and NLG.
Natural Language Understanding
Task-Oriented Dialogue Systems
+1
Dialogue manager domain adaptation using Gaussian process reinforcement learning
Spoken dialogue systems allow humans to interact with machines using natural speech.
Conditional Generation and Snapshot Learning in Neural Dialogue Systems
Recently a variety of LSTM-based conditional language models (LM) have been applied across a range of language generation tasks.
Continuously Learning Neural Dialogue Management
We describe a two-step approach for dialogue management in task-oriented spoken dialogue systems.
On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems
The ability to compute an accurate reward function is essential for optimising a dialogue policy via reinforcement learning.
A Network-based End-to-End Trainable Task-oriented Dialogue System
Teaching machines to accomplish tasks by conversing naturally with humans is challenging.
Multi-domain Neural Network Language Generation for Spoken Dialogue Systems
Moving from limited-domain natural language generation (NLG) to open domain is difficult because the number of semantic input combinations grows exponentially with the number of domains.
Counter-fitting Word Vectors to Linguistic Constraints
In this work, we present a novel counter-fitting method which injects antonymy and synonymy constraints into vector space representations in order to improve the vectors' capability for judging semantic similarity.
Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems
Reward shaping is one promising technique for addressing these concerns.
Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems
The models are trained on dialogues generated by a simulated user and the best model is then used to train a policy on-line which is shown to perform at least as well as a baseline system using prior knowledge of the user's task.
Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking
The natural language generation (NLG) component of a spoken dialogue system (SDS) usually needs a substantial amount of handcrafting or a well-labeled dataset to be trained on.
Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact both on usability and perceived quality.
Multi-domain Dialog State Tracking using Recurrent Neural Networks
Dialog state tracking is a key component of many modern dialog systems, most of which are designed with a single, well-defined domain in mind.
