Neural models of factuality
This work addresses event factuality prediction for natural language processing applications, but it is incremental as it builds on existing datasets and methods.
The authors tackled event factuality prediction by developing two neural models that achieved significant performance gains over previous models on three datasets (FactBank, UW, and MEANTIME), and they expanded the It Happened portion of the Universal Decompositional Semantics dataset to create the largest event factuality dataset to date, reporting results on this extended dataset.
We present two neural models for event factuality prediction, which yield significant performance gains over previous models on three event factuality datasets: FactBank, UW, and MEANTIME. We also present a substantial expansion of the It Happened portion of the Universal Decompositional Semantics dataset, yielding the largest event factuality dataset to date. We report model results on this extended factuality dataset as well.