论文标题
已发送：句子级梁搜索可控摘要
SentBS: Sentence-level Beam Search for Controllable Summarization
论文作者
论文摘要
在可控制的文本生成中已经探索了广泛的控制观点。结构控制的摘要最近被提出是一个有用且有趣的研究方向。但是，当前的结构控制方法在执行所需结构方面的有效性有限。为了解决此限制，我们提出了一个句子级梁搜索方法（已发送），在整个生成过程中进行评估以选择随后的一代的合适句子。我们尝试通过发送BS来实验解码方法的不同组合，以用作子组件，并评估结构控制的数据集Mred的结果。实验表明，所有探索的SEDBS组合都可以改善生成的文本与所需结构之间的一致性，最佳方法将现有模型遭受的结构差异显着降低了约68％。
A wide range of control perspectives have been explored in controllable text generation. Structure-controlled summarization is recently proposed as a useful and interesting research direction. However, current structure-controlling methods have limited effectiveness in enforcing the desired structure. To address this limitation, we propose a sentence-level beam search generation method (SentBS), where evaluation is conducted throughout the generation process to select suitable sentences for subsequent generations. We experiment with different combinations of decoding methods to be used as subcomponents by SentBS and evaluate results on the structure-controlled dataset MReD. Experiments show that all explored combinations for SentBS can improve the agreement between the generated text and the desired structure, with the best method significantly reducing the structural discrepancies suffered by the existing model, by approximately 68%.
