Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Skeleton-based Coherence Modeling in Narratives

Nishit Asnani, Rohan Badlani

Abstract

Modeling coherence in text has been a task that has excited NLP researchers since a long time. It has applications in detecting incoherent structures and helping the author fix them. There has been recent work in using neural networks to extract a skeleton from one sentence, and then use that skeleton to generate the next sentence for coherent narrative story generation. In this project, we aim to study if the consistency of skeletons across subsequent sentences is a good metric to characterize the coherence of a given body of text. We propose a new Sentence/Skeleton Similarity Network (SSN) for modeling coherence across pairs of sentences, and show that this network performs much better than baseline similarity techniques like cosine similarity and Euclidean distance. Although skeletons appear to be promising candidates for modeling coherence, our results show that sentence-level models outperform those on skeletons for evaluating textual coherence, thus indicating that the current state-of-the-art coherence modeling techniques are going in the right direction by dealing with sentences rather than their sub-parts.

Skeleton-based Coherence Modeling in Narratives

Abstract

Modeling coherence in text has been a task that has excited NLP researchers since a long time. It has applications in detecting incoherent structures and helping the author fix them. There has been recent work in using neural networks to extract a skeleton from one sentence, and then use that skeleton to generate the next sentence for coherent narrative story generation. In this project, we aim to study if the consistency of skeletons across subsequent sentences is a good metric to characterize the coherence of a given body of text. We propose a new Sentence/Skeleton Similarity Network (SSN) for modeling coherence across pairs of sentences, and show that this network performs much better than baseline similarity techniques like cosine similarity and Euclidean distance. Although skeletons appear to be promising candidates for modeling coherence, our results show that sentence-level models outperform those on skeletons for evaluating textual coherence, thus indicating that the current state-of-the-art coherence modeling techniques are going in the right direction by dealing with sentences rather than their sub-parts.

Paper Structure

This paper contains 13 sections, 6 equations, 2 figures.

Table of Contents

  1. Introduction
  2. Related work
  3. Approach
  4. Experiments
  5. Data and necessary preprocessing
  6. Evaluation Metrics
  7. Evaluation Details
  8. Results and Analysis
  9. Conclusion
  10. Future Work and Extensions
  11. Acknowledgements
  12. Appendix
  13. Code

Figures (2)

  • Figure 1: Skeleton-based Model for generating narratives, with test phase and training phase clearly demarcated.
  • Figure 2: Skeleton Similarity Network. For the experiments where the attention layer is removed, we use the output from the final encoder LSTM as the sentence embedding.