activity
20162024
most citedEvaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge

185 citations · 553 across the 31 of their papers we have counts for

collaborators
Showing 2018 · cs.CLShow all

6 papers · 2 filters

cs.CL2018

Improving Context Modelling in Multimodal Dialogue Generation

Shubham Agarwal, Ondrej Dusek, Ioannis Konstas +1

In this work, we investigate the task of textual response generation in a multimodal task-oriented dialogue system. Our work is based on the recently released Multimodal Dialogue (…

cs.CL2018

A Knowledge-Grounded Multimodal Search-Based Conversational Agent

Shubham Agarwal, Ondrej Dusek, Ioannis Konstas +1

Multimodal search-based dialogue is a challenging new task: It extends visually grounded question answering systems into multi-turn conversations with access to an external databas…

cs.CL2018

Findings of the E2E NLG Challenge

Ondřej Dušek, Jekaterina Novikova, Verena Rieser

This paper summarises the experimental setup and results of the first shared task on end-to-end (E2E) natural language generation (NLG) in spoken dialogue systems. Recent end-to-en…

cs.CL2018

Better Conversations by Modeling,Filtering,and Optimizing for Coherence and Diversity

Xinnuo Xu, Ondřej Dušek, Ioannis Konstas +1

We present three enhancements to existing encoder-decoder models for open-domain conversational agents, aimed at effectively modeling coherence and promoting output diversity: (1)…

cs.CL2018

Towards Learning Transferable Conversational Skills using Multi-dimensional Dialogue Modelling

Simon Keizer, Verena Rieser

Recent statistical approaches have improved the robustness and scalability of spoken dialogue systems. However, despite recent progress in domain adaptation, their reliance on in-d…

cs.CL2018

RankME: Reliable Human Ratings for Natural Language Generation

Jekaterina Novikova, Ondřej Dušek, Verena Rieser

Human evaluation for natural language generation (NLG) often suffers from inconsistent user ratings. While previous research tends to attribute this problem to individual user pref…