Yaji Sripada


2024

pdf
Improving Factual Accuracy of Neural Table-to-Text Output by Addressing Input Problems in ToTTo
Barkavi Sundararajan | Yaji Sripada | Ehud Reiter
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

Neural Table-to-Text models tend to hallucinate, producing texts that contain factual errors. We investigate whether such errors in the output can be traced back to problems with the input. We manually annotated 1,837 texts generated by multiple models in the politics domain of the ToTTo dataset. We identify the input problems that are responsible for many output errors and show that fixing these inputs reduces factual errors by between 52% and 76% (depending on the model). In addition, we observe that models struggle in processing tabular inputs that are structured in a non-standard way, particularly when the input lacks distinct row and column values or when the column headers are not correctly mapped to corresponding values.

2021

pdf bib
Proceedings of the 14th International Conference on Natural Language Generation
Anya Belz | Angela Fan | Ehud Reiter | Yaji Sripada
Proceedings of the 14th International Conference on Natural Language Generation

2020

pdf bib
Proceedings of the 13th International Conference on Natural Language Generation
Brian Davis | Yvette Graham | John Kelleher | Yaji Sripada
Proceedings of the 13th International Conference on Natural Language Generation

2015

pdf
Designing an Algorithm for Generating Named Spatial References
Rodrigo de Oliveira | Yaji Sripada | Ehud Reiter
Proceedings of the 15th European Workshop on Natural Language Generation (ENLG)

2009

pdf
Generating Approximate Geographic Descriptions
Ross Turner | Yaji Sripada | Ehud Reiter
Proceedings of the 12th European Workshop on Natural Language Generation (ENLG 2009)

2008

pdf
What’s In a Message? Interpreting Geo-referenced Data for the Visually-impaired
Kavita Thomas | Yaji Sripada
Proceedings of the Fifth International Natural Language Generation Conference