Search Results for author:
Found 11 papers, 2 papers with code
Studying the Impact of Filling Information Gaps on the Output Quality of Neural Data-to-Text
It is unfair to expect neural data-to-text to produce high quality output when there are gaps between system input data and information contained in the training text.
Improving Factual Accuracy of Neural Table-to-Text Output by Addressing Input Problems in ToTTo
Neural Table-to-Text models tend to hallucinate, producing texts that contain factual errors.
SportSett:Basketball - A robust and maintainable dataset for Natural Language Generation
In this resource paper, we introduce the SportSett:Basketball database.
Comprehension Driven Document Planning in Natural Language Generation Systems
This paper proposes an approach to NLG system design which focuses on generating output text which can be more easily processed by the reader.
Towards making NLG a voice for interpretable Machine Learning
This paper presents a study to understand the issues related to using NLG to humanise explanations from a popular interpretable machine learning framework called LIME.
BIG-bench Machine Learning
Interpretable Machine Learning
+1
Textually Summarising Incomplete Data
Many data-to-text NLG systems work with data sets which are incomplete, ie some of the data is missing.
