Document Level Hierarchical Transformer

Generating long and coherent text is an important and challenging task encompassing many application areas such as summarization, document level machine translation and story generation. Despite the success in modeling intra-sentence coherence, existing long text generation models (e.g., BART and GPT-3) still struggle to maintain a coherent event sequence throughout the generated text. We conjecture that this is because of the difficulty for the model to revise, replace, revoke or delete any part that has been generated by the model. In this paper, we present a novel semi-autoregressive document generation model capable of revising and editing the generated text. Building on recent models by (Gu et al., 2019; Xu and Carpuat, 2020) we propose document generation as a hierarchical Markov decision process with a two level hierarchy, where the high and low level editing programs. We train our model using imitation learning (Hussein et al., 2017) and introduce roll-in policy such that each policy learns on the output of applying the previous action. Experiments applying the proposed approach sheds various insights on the problems of long text generation using our model. We suggest various remedies such as using distilled dataset, designing better attention mechanisms and using autoregressive models as a low level program.