arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.08647cs.CLcs.LG
收藏

利用依赖图进行问题分解

Question Decomposition with Dependency Graphs

Tel Aviv University(特拉维夫大学)

Matan Hasson, Jonathan Berant

摘要:

QDMR是一种复杂问题的意义表示方法,它将问题分解为一系列原子步骤。虽然最先进的QDMR解析器使用常见的序列到序列(seq2seq)方法,但QDMR结构从根本上描述了输入问题中跨度之间的标记关系,因此基于依赖性的方法似乎适合于此任务。在这项工作中,我们提出了一个QDMR解析器,它是基于依赖图(DG),其中图中的节点是单词和边缘描述的逻辑关系,对应于不同的计算步骤。我们提出了(a)一个非自回归图解析器,其中所有的图边同时计算,和(b)一个seq2seq解析器,使用黄金图作为辅助监督。我们发现,图解析器导致性能适度降低(0.47至0.44),但由于解析器的非自回归性质,推理时间加快了16倍,并且与seq2seq模型相比,提高了样本复杂度。其次,与seq2seq模型相比,使用辅助图监督训练的seq2seq模型对新领域具有更好的泛化能力,并且在具有长计算步骤序列的问题上也表现得更好。

英文摘要:

QDMR is a meaning representation for complex questions, which decomposes questions into a sequence of atomic steps. While state-of-the-art QDMR parsers use the common sequence-to-sequence (seq2seq) approach, a QDMR structure fundamentally describes labeled relations between spans in the input question, and thus dependency-based approaches seem appropriate for this task. In this work, we present a QDMR parser that is based on dependency graphs (DGs), where nodes in the graph are words and edges describe logical relations that correspond to the different computation steps. We propose (a) a non-autoregressive graph parser, where all graph edges are computed simultaneously, and (b) a seq2seq parser that uses gold graph as auxiliary supervision. We find that a graph parser leads to a moderate reduction in performance (0.47 to 0.44), but to a 16x speed-up in inference time due to the non-autoregressive nature of the parser, and to improved sample complexity compared to a seq2seq model. Second, a seq2seq model trained with auxiliary graph supervision has better generalization to new domains compared to a seq2seq model, and also performs better on questions with long sequences of computation steps.

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。

↑