Summarize, Outline, and Elaborate: Long-Text Generation via Hierarchical Supervision from Extractive Summaries
Preprint
Abstract
The difficulty of generating coherent long texts lies in the fact that existing models overwhelmingly focus on predicting local words, and cannot make high level plans on what to generate or capture the high-level discourse dependencies between chunks of texts. Inspired by human writing processes, where a list of bullet points or a catalog is first outlined, and then each bullet point is expanded to form the whole article, we propose {\it SOE}, a pipelined system that involves of summarizing, outlining and elaborating for long text generation: the model first outlines the summaries for different segments of long texts, and then elaborates on each bullet point to generate the corresponding segment. To avoid the labor-intensive process of summary soliciting, we propose the {\it reconstruction} strategy, which extracts segment summaries in an unsupervised manner by selecting its most informative part to reconstruct the segment. The proposed generation system comes with the following merits: (1) the summary provides high-level guidance for text generation and avoids the local minimum of individual word predictions; (2) the high-level discourse dependencies are captured in the conditional dependencies between summaries and are preserved during the summary expansion process and (3) additionally, we are able to consider significantly more contexts by representing contexts as concise summaries. Extensive experiments demonstrate that SOE produces long texts with significantly better quality, along with faster convergence speed.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Blank Language Models2020
- Sentence-Level Content Planning and Style Specification for Neural Text Generation2019
- Order-Planning Neural Text Generation From Structured DataProceedings of the AAAI Conference on Artificial Intelligence, 2018
- Learning Neural Templates for Text Generation2018
- Bottom-Up Abstractive Summarization2018
- A Skeleton-Based Model for Promoting Coherence Among Sentences in Narrative Story Generation2018
- Adversarial Learning for Neural Dialogue Generation2017
- Neural Net Models of Open-domain Discourse Coherence2017
- Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books2015
- Effective Approaches to Attention-based Neural Machine Translation2015