1 code implementation • INLG (ACL) 2020 • Craig Thomson, Zhijie Zhao, Somayajulu Sripada
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.
1 code implementation • 5 Apr 2024 • Barkavi Sundararajan, Somayajulu Sripada, Ehud Reiter
Neural Table-to-Text models tend to hallucinate, producing texts that contain factual errors.
no code implementations • IntelLang 2020 • Craig Thomson, Ehud Reiter, Somayajulu Sripada
In this resource paper, we introduce the SportSett:Basketball database.
no code implementations • WS 2018 • Craig Thomson, Ehud Reiter, Somayajulu Sripada
This paper proposes an approach to NLG system design which focuses on generating output text which can be more easily processed by the reader.
no code implementations • WS 2018 • James Forrest, Somayajulu Sripada, Wei Pang, George Coghill
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
no code implementations • WS 2017 • Stephanie Inglis, Ehud Reiter, Somayajulu Sripada
Many data-to-text NLG systems work with data sets which are incomplete, ie some of the data is missing.