One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases
This addresses a key limitation in keyphrase generation for text analysis, though it is incremental in improving existing models.
The authors tackled the problem that existing neural keyphrase generation models cannot naturally produce a variable number of keyphrases, proposing a recurrent generative model with techniques to enhance diversity and control output count, along with new evaluation metrics and a dataset. Their model outperformed strong baselines on all datasets using both previous and new metrics.
Different texts shall by nature correspond to different number of keyphrases. This desideratum is largely missing from existing neural keyphrase generation models. In this study, we address this problem from both modeling and evaluation perspectives. We first propose a recurrent generative model that generates multiple keyphrases as delimiter-separated sequences. Generation diversity is further enhanced with two novel techniques by manipulating decoder hidden states. In contrast to previous approaches, our model is capable of generating diverse keyphrases and controlling number of outputs. We further propose two evaluation metrics tailored towards the variable-number generation. We also introduce a new dataset StackEx that expands beyond the only existing genre (i.e., academic writing) in keyphrase generation tasks. With both previous and new evaluation metrics, our model outperforms strong baselines on all datasets.