SARG：一种新的用于多圈不完全语音恢复的半自回归发生器
SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration
摘要：
开放领域的对话系统由于单轮语料的易得和深度学习的发展而取得了巨大的成功，但多轮场景由于频繁的共指和信息遗漏仍然是一个挑战。在本文中，我们研究了不完整的话语恢复，带来了普遍的改善，多轮对话系统在最近的研究。同时，在自回归文本生成和序列标记文本编辑的启发下，提出了一种高效、灵活的半自回归生成器（SARG）。此外，在两个基准测试上的实验表明，我们提出的模型在质量和推理速度方面明显优于最先进的模型。
英文摘要：
Dialogue systems in open domain have achieved great success due to the easily obtained single-turn corpus and the development of deep learning, but the multi-turn scenario is still a challenge because of the frequent coreference and information omission. In this paper, we investigate the incomplete utterance restoration which has brought general improvement over multi-turn dialogue systems in recent studies. Meanwhile, jointly inspired by the autoregression for text generation and the sequence labeling for text editing, we propose a novel semi autoregressive generator (SARG) with the high efficiency and flexibility. Moreover, experiments on two benchmarks show that our proposed model significantly outperforms the state-of-the-art models in terms of quality and inference speed.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
