Generating Descriptions from Structured Data Using a Bifocal Attention Mechanism and Gated Orthogonalization

doi link
Published in "In Proceedings of the North American Chapter of the Association for Computational Linguistics"
Preksha Nema , Shreyas Shetty M , Parag Jain , Anirban Laha , Karthik Sankaranarayanan , Mitesh M. Khapra
seq2seq , bifocal attention mechanism , gated orthogonalization

In this work, we focus on the task of generating natural language descriptions from a structured table of facts containing fields (such as nationality, occupation, etc) and values (such as Indian, actor, director, etc). One simple choice is to treat the table as a sequence of fields and values and then use a standard seq2seq model for this task.