Using Sentence-Level LSTM Language Models for Script Inference
This addresses script inference for NLP applications, but it is incremental as it compares existing methods without introducing a new approach.
The paper tackled the problem of probabilistic inference of implicit events from documents by comparing structured statistical script systems with sentence-level LSTM language models, finding that the neural models are roughly comparable to the structured systems in predicting missing events.
There is a small but growing body of research on statistical scripts, models of event sequences that allow probabilistic inference of implicit events from documents. These systems operate on structured verb-argument events produced by an NLP pipeline. We compare these systems with recent Recurrent Neural Net models that directly operate on raw tokens to predict sentences, finding the latter to be roughly comparable to the former in terms of predicting missing events in documents.