S
Somayajulu Sripada
Researcher at University of Aberdeen
Publications - 79
Citations - 2287
Somayajulu Sripada is an academic researcher from University of Aberdeen. The author has contributed to research in topics: Natural language generation & Passenger information. The author has an hindex of 24, co-authored 78 publications receiving 2168 citations. Previous affiliations of Somayajulu Sripada include King's College, Aberdeen.
Papers
More filters
Journal ArticleDOI
Choosing words in computer-generated weather forecasts
TL;DR: An evaluation by forecast users suggested that they preferred SumTime-Mousam's texts to human-generated texts, in part because of better word choice; this may be the first time that an evaluation has shown that nlg texts are better than human-authored texts.
Journal ArticleDOI
Automatic generation of textual summaries from neonatal intensive care data
François Portet,Ehud Reiter,Albert Gatt,Jim Hunter,Somayajulu Sripada,Yvonne Freer,Cindy Sykes +6 more
TL;DR: A prototype, called BT-45, is presented, which generates textual summaries of about 45 minutes of continuous physiological signals and discrete events and brings together techniques from the different areas of signal processing, medical reasoning, knowledge engineering, and natural language generation.
Book ChapterDOI
Automatic Generation of Textual Summaries from Neonatal Intensive Care Data
TL;DR: A prototype is being developed which will generate a textual summary of 45 minutes of continuous physiological signals and discrete events, which brings together techniques from the different areas of signal analysis, medical reasoning, and natural language generation.
Journal ArticleDOI
From data to text in the Neonatal Intensive Care Unit: Using NLG technology for decision support and information management
Albert Gatt,François Portet,Ehud Reiter,Jim Hunter,Saad Mahamood,Wendy Moncur,Somayajulu Sripada +6 more
TL;DR: Recent and ongoing work on building systems that automatically generate textual summaries of neonatal data are described, showing that the technology is viable and comparable in its effectiveness for decision support to existing presentation modalities.
Journal ArticleDOI
Acquiring correct knowledge for natural language generation
TL;DR: Understanding how individual KA techniques can fail, and using a mixture of different KA technique with different strengths and weaknesses, can help developers acquire NLG knowledge that is mostly correct.