Verena Rieser

Crowd-sourcing NLG Data: Pictures Elicit Better Data.

2016

Recent advances in corpus-based Natural Language Generation (NLG) hold the promise of being easily portable across domains, but require costly training data, consisting of meaning representations (MRs) paired with Natural Language (NL) utterances. In this …

Alana: Social Dialogue using an Ensemble Model and a Ranker trained on User Feedback

2017 · Edinburgh Napier Research Repository (Edinburgh Napier University)

We describe our Alexa prize system (called ‘Alana’) which consists of an ensemble of bots, combining rule-based and machine learning systems, and using a contextual ranking mechanism to choose system responses. This paper reports on …

Benchmarking Natural Language Understanding Services for building Conversational Agents

2019 · arXiv (Cornell University)

We have recently seen the emergence of several publicly available Natural Language Understanding (NLU) toolkits, which map user utterances to structured, but more abstract, Dialogue Act (DA) or Intent specifications, while making this process accessible …

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

2018

We present three enhancements to existing encoder-decoder models for open-domain conversational agents, aimed at effectively modeling coherence and promoting output diversity: (1) We introduce a measure of coherence as the GloVe embedding similarity between the …

Evaluating the state-of-the-art of End-to-End Natural Language Generation: The E2E NLG challenge

2019 · Computer Speech & Language

This paper provides a comprehensive analysis of the first shared task on End-to-End Natural Language Generation (NLG) and identifies avenues for future research based on the results. This shared task aimed to assess whether recent …