The ability to consolidate information of different types is at the core of
intelligence, and has tremendous practical value in allowing learning for one
task to benefit from generalizations learned for others. In this paper we
tackle the challenging task of improving semantic parsing performance, taking
UCCA parsing as a test case, and AMR, SDP and Universal Dependencies (UD)
parsing as auxiliary tasks. We experiment on three languages, using a uniform
transition-based system and learning architecture for all parsing tasks.
Despite notable conceptual, formal and domain differences, we show that
multitask learning significantly improves UCCA parsing in both in-domain and
out-of-domain settings.

本文针对语义解析的性能进行改进，使用多任务学习方法，将 UCCA 解析作为测试案例，辅助任务包括 AMR 解析、SDP 解析和 Universal Dependencies 解析。实验表明，多任务学习显著提高了 UCCA 解析的性能。

跨语义表示的多任务解析

Multitask Parsing Across Semantic Representations

Sequence-to-sequence models have shown strong performance across a broad
range of applications. However, their application to parsing and generating
text usingAbstract Meaning Representation (AMR)has been limited, due to the
relatively limited amount of labeled data and the non-sequential nature of the
AMR graphs. We present a novel training procedure that can lift this limitation
using millions of unlabeled sentences and careful preprocessing of the AMR
graphs. For AMR parsing, our model achieves competitive results of 62.1SMATCH,
the current best score reported without significant use of external semantic
resources. For AMR generation, our model establishes a new state-of-the-art
performance of BLEU 33.8. We present extensive ablative and qualitative
analysis including strong evidence that sequence-based AMR models are robust
against ordering variations of graph-to-sequence conversions.

使用数百万个未标记的句子和对 AMR 图的精心预处理，我们提出了一种新颖的训练过程，成功地解决了 AMR 中有限的标记数据和非顺序的图表征对序列到序列模型的限制。我们在 AMR 解析和生成任务上取得了竞争性结果，并得到了丰富的分析和证据表明序列基 AMR 模型对图表征的排序变化具有鲁棒性。

神经 AMR: 序列到序列模型用于解析和生成

Neural AMR: Sequence-to-Sequence Models for Parsing and Generation

Neural attention models have achieved great success in different NLP tasks.
How- ever, they have not fulfilled their promise on the AMR parsing task due to
the data sparsity issue. In this paper, we de- scribe a sequence-to-sequence
model for AMR parsing and present different ways to tackle the data sparsity
problem. We show that our methods achieve significant improvement over a
baseline neural atten- tion model and our results are also compet- itive
against state-of-the-art systems that do not use extra linguistic resources.

本文提出了一种基于序列到序列模型的方法来解决 AMR（抽象语义表示）解析任务中的数据稀疏问题，并与使用额外的语言资源的最先进系统进行了竞争，并表明我们的方法取得了显著的改进。