Sequence to Sequence Learning for Event Prediction
This work addresses event prediction in natural language processing, offering incremental improvements over existing methods.
The paper tackles the problem of predicting event descriptions from preceding sentences in text, using a bidirectional multi-layer recurrent neural network for sequence-to-sequence learning, and reports substantial improvements in BLEU scores on WikiHow and DeScript datasets, complemented by a linguistic evaluation.
This paper presents an approach to the task of predicting an event description from a preceding sentence in a text. Our approach explores sequence-to-sequence learning using a bidirectional multi-layer recurrent neural network. Our approach substantially outperforms previous work in terms of the BLEU score on two datasets derived from WikiHow and DeScript respectively. Since the BLEU score is not easy to interpret as a measure of event prediction, we complement our study with a second evaluation that exploits the rich linguistic annotation of gold paraphrase sets of events.