Long Text Generation by Modeling Sentence-Level and Discourse-Level Coherence

• URL: http://arxiv.org/abs/2105.08963v1
• Date: Wed, 19 May 2021 07:29:08 GMT
• Title: Long Text Generation by Modeling Sentence-Level and Discourse-Level Coherence
• Authors: Jian Guan, Xiaoxi Mao, Changjie Fan, Zitao Liu, Wenbiao Ding, Minlie Huang
• Abstract summary: We propose a long text generation model, which can represent the prefix sentences at sentence level and discourse level in the decoding process. Our model can generate more coherent texts than state-of-the-art baselines.
• Score: 59.51720326054546
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating long and coherent text is an important but challenging task, particularly for open-ended language generation tasks such as story generation. Despite the success in modeling intra-sentence coherence, existing generation models (e.g., BART) still struggle to maintain a coherent event sequence throughout the generated text. We conjecture that this is because of the difficulty for the decoder to capture the high-level semantics and discourse structures in the context beyond token-level co-occurrence. In this paper, we propose a long text generation model, which can represent the prefix sentences at sentence level and discourse level in the decoding process. To this end, we propose two pretraining objectives to learn the representations by predicting inter-sentence semantic similarity and distinguishing between normal and shuffled sentence orders. Extensive experiments show that our model can generate more coherent texts than state-of-the-art baselines.

Related papers

• Sequentially Controlled Text Generation [97.22539956688443]
  GPT-2 generates sentences that are remarkably human-like, longer documents can ramble and do not follow human-like writing structure. We study the problem of imposing structure on long-range text. We develop a sequential controlled text generation pipeline with generation and editing.
  arXiv  Detail & Related papers  (2023-01-05T21:23:51Z)
• Model Criticism for Long-Form Text Generation [113.13900836015122]
  We apply a statistical tool, model criticism in latent space, to evaluate the high-level structure of generated text. We perform experiments on three representative aspects of high-level discourse -- coherence, coreference, and topicality. We find that transformer-based language models are able to capture topical structures but have a harder time maintaining structural coherence or modeling coreference.
  arXiv  Detail & Related papers  (2022-10-16T04:35:58Z)
• Event Transition Planning for Open-ended Text Generation [55.729259805477376]
  Open-ended text generation tasks require models to generate a coherent continuation given limited preceding context. We propose a novel two-stage method which explicitly arranges the ensuing events in open-ended text generation. Our approach can be understood as a specially-trained coarse-to-fine algorithm.
  arXiv  Detail & Related papers  (2022-04-20T13:37:51Z)
• PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation [47.97523895218194]
  We propose a novel generation framework leveraging autoregressive self-attention mechanism to conduct content planning and surface realization dynamically. Our framework enriches the Transformer decoder with latent representations to maintain sentence-level semantic plans grounded by bag-of-words.
  arXiv  Detail & Related papers  (2022-03-17T05:52:35Z)
• Discontinuous Grammar as a Foreign Language [0.7412445894287709]
  We extend the framework of sequence-to-sequence models for constituent parsing. We design several novelizations that can fully produce discontinuities. For the first time, we test a sequence-to-sequence model on the main discontinuous benchmarks.
  arXiv  Detail & Related papers  (2021-10-20T08:58:02Z)
• DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformer [40.10695204278747]
  We propose DiscoDVT, a discourse-aware discrete variational Transformer to tackle the incoherence issue. We conduct extensive experiments on two open story generation datasets and demonstrate that the latent codes learn meaningful correspondence to the discourse structures that guide the model to generate long texts with better long-range coherence.
  arXiv  Detail & Related papers  (2021-10-12T13:41:06Z)
• Lexically-constrained Text Generation through Commonsense Knowledge Extraction and Injection [62.071938098215085]
  We focus on the Commongen benchmark, wherein the aim is to generate a plausible sentence for a given set of input concepts. We propose strategies for enhancing the semantic correctness of the generated text.
  arXiv  Detail & Related papers  (2020-12-19T23:23:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.