A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation

August 21, 2018 · Entered Twilight · 🏛 Conference on Empirical Methods in Natural Language Processing

"Last commit was 7.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: README.md, __init__.py, batcher.py, calculate_relevance_BLEU.py, data.py, data, decode.py, generate_sc_sample.py, generated_sample.py, generated_srl_sample.py, generator_whole.py, inspect_checkpoint.py, model.py, result_evaluate.py, run_summarization.py, run_test.sh, run_train.sh, sc_batch.py, sc_model.py, srl_seq_batch.py, srl_seq_model.py, util.py

Authors Jingjing Xu, Xuancheng Ren, Yi Zhang, Qi Zeng, Xiaoyan Cai, Xu Sun arXiv ID 1808.06945 Category cs.CL: Computation & Language Citations 108 Venue Conference on Empirical Methods in Natural Language Processing Repository https://github.com/lancopku/Skeleton-Based-Generation-Model ⭐ 63 Last Checked 1 month ago

Abstract

Narrative story generation is a challenging problem because it demands the generated sentences with tight semantic connections, which has not been well studied by most existing generative models. To address this problem, we propose a skeleton-based model to promote the coherence of generated stories. Different from traditional models that generate a complete sentence at a stroke, the proposed model first generates the most critical phrases, called skeleton, and then expands the skeleton to a complete and fluent sentence. The skeleton is not manually defined, but learned by a reinforcement learning method. Compared to the state-of-the-art models, our skeleton-based model can generate significantly more coherent text according to human evaluation and automatic evaluation. The G-score is improved by 20.1% in the human evaluation. The code is available at https://github.com/lancopku/Skeleton-Based-Generation-Model