Jekaterina Novikova

Crowd-sourcing NLG Data: Pictures Elicit Better Data.

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 work, we propose a novel framework for crowdsourcing high quality NLG training data, using automatic quality control measures and evaluating different MRs with which to elicit data. We show that pictorial MRs result in better NL data being collected than logic-based MRs: utterances elicited by pictorial MRs are judged as significantly more natural, more informative, and better phrased, with a significant increase in average quality ratings (around 0.5 points on a 6-point scale), compared to using the logical MRs. As the MR becomes more complex, the benefits of pictorial stimuli increase. The collected data will be released as part of this submission.

The aNALoGuE Challenge: Non Aligned Language GEneration

We propose a shared task based on recent advances in learning to generate natural language from meaning representations using semantically unaligned data. The aNALoGuE challenge aims to evaluate and compare recent corpus-based methods with respect to their scalability to data size and target complexity, as well as to assess predictive quality of automatic evaluation metrics.

Introducing a ROS based planning and execution framework for human-robot interaction

Working in human populated environments requires fast and robust action selection and execution especially when deliberately trying to interact with humans. This work presents the combination of a high-level planner (ROSPlan) for action sequencing and automatically generated finite state machines (PNP) for execution. Using this combined system we are able to exploit the speed and robustness of the execution and the flexibility of the sequence generation and combine the positive aspects of both approaches.