Conversational Semantic Parsing
Conversational Semantic Parsing
复制标题
会话语义解析
DOI：
10.18653/v1/2020.emnlp-main.408
复制
发表时间：
2020
影响因子：
2.8
通讯作者：
S. Gupta
中科院分区：
文献类型：
--
作者：
Armen Aghajanyan;Jean Maillard;Akshat Shrivastava;K. Diedrick;Mike Haeger;Haoran Li;Yashar Mehdad;Ves Stoyanov;Anuj Kumar;M. Lewis;S. Gupta
面向任务的辅助系统中的语义解析的结构化表示是面向简单理解的一轮查询。由于表示的局限性，基于会话的属性，如共指消解和上下文结转在流水线系统中的下游处理。在本文中，我们提出了一个语义表示这种面向任务的会话系统，可以表示概念，如共同引用和上下文结转，使全面理解的查询会话。我们发布了一个新的基于会话的，面向任务的分析数据集，包含20k会话，由60k话语组成。与对话状态跟踪挑战不同，数据集中的查询具有组合形式。我们提出了一个新的系列Seq2Seq模型的会话为基础的解析上面，实现更好的或相当的性能，目前国家的最先进的ATIS，SNIPS，TOP和DSTC 2。值得注意的是，我们将DSTC 2上最知名的结果提高了5个点。
The structured representation for semantic parsing in task-oriented assistant systems is geared towards simple understanding of one-turn queries. Due to the limitations of the representation, the session-based properties such as co-reference resolution and context carryover are processed downstream in a pipelined system. In this paper, we propose a semantic representation for such task-oriented conversational systems that can represent concepts such as co-reference and context carryover, enabling comprehensive understanding of queries in a session. We release a new session-based, compositional task-oriented parsing dataset of 20k sessions consisting of 60k utterances. Unlike Dialog State Tracking Challenges, the queries in the dataset have compositional forms. We propose a new family of Seq2Seq models for the session-based parsing above, which achieve better or comparable performance to the current state-of-the-art on ATIS, SNIPS, TOP and DSTC2. Notably, we improve the best known results on DSTC2 by up to 5 points for slot-carryover.