collaborators

6 papers

cs.CL2016

Conditional Generation and Snapshot Learning in Neural Dialogue Systems

Tsung-Hsien Wen, Milica Gasic, Nikola Mrksic +5

Recently a variety of LSTM-based conditional language models (LM) have been applied across a range of language generation tasks. In this work we study various model architectures a…

cs.CL2016

Continuously Learning Neural Dialogue Management

Pei-Hao Su, Milica Gasic, Nikola Mrksic +5

We describe a two-step approach for dialogue management in task-oriented spoken dialogue systems. A unified neural network framework is proposed to enable the system to first learn…

cs.CL2016

On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems

Pei-Hao Su, Milica Gasic, Nikola Mrksic +5

The ability to compute an accurate reward function is essential for optimising a dialogue policy via reinforcement learning. In real-world applications, using explicit user feedbac…

cs.CL2016

Multi-domain Neural Network Language Generation for Spoken Dialogue Systems

Tsung-Hsien Wen, Milica Gasic, Nikola Mrksic +4

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 do…

cs.CL2016

Counter-fitting Word Vectors to Linguistic Constraints

Nikola Mrkšić, Diarmuid Ó Séaghdha, Blaise Thomson +6

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' capabilit…

cs.CL2015

Multi-domain Dialog State Tracking using Recurrent Neural Networks

Nikola Mrkšić, Diarmuid Ó Séaghdha, Blaise Thomson +5

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. This paper shows that dialog data dra…