HLT@SUDA at SemEval-2019 Task 1: UCCA Graph Parsing as Constituent Tree Parsing

Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval-2019), pages 11–15 Minneapolis, Minnesota, USA, June 6–7, 2019. ©2019 Association for Computational Linguistics 11 HLT@SUDA at SemEval-2019 Task 1: UCCA Graph Parsing as Constituent Tree Parsing Wei Jiang, Zhenghua Li∗, Yu Zhang, Min Zhang School of Computer Science and Technology, Soochow University, China {wjiang0501, yzhang25}@stu.suda.edu.cn, {zhli13,minzhang}@suda.edu.cn Abstract This paper describes a simple UCCA semantic graph parsing approach. The key idea is to convert a UCCA semantic graph into a constituent tree, in which extra labels are deliberately designed to mark remote edges and discontinuous nodes for future recovery. In this way, we can make use of existing syntactic parsing techniques. Based on the data statistics, we recover discontinuous nodes directly according to the output labels of the constituent parser and use a biaffine classification model to recover the more complex remote edges. The classification model and the constituent parser are simultaneously trained under the multi-task learning framework. We use the multilingual BERT as extra features in the open tracks. Our system ranks the first place in the six English/German closed/open tracks among seven participating systems. For the seventh cross-lingual track, where there is little training data for French, we propose a language embedding approach to utilize English and German training data, and our result ranks the second place. 1 Introduction Universal Conceptual Cognitive Annotation (UCCA) is a multi-layer linguistic framework for semantic annotation proposed by Abend and Rappoport (2013). Figure 1 shows an example sentence and its UCCA graph. Words are represented as terminal nodes. Circles denote non-terminal nodes, and the semantic relation ∗Corresponding author, hlt.suda.edu.cn/zhenghua 1 2 H 3 4 “ 5 lch 6 ging umher A 7 und A 8 tastete 9 . H U A P L A H P U Figure 1: A UCCA graph example from the German data. The English translation is “ I went around and groped . We assign a number to each non-terminal node to facilitate illustration. between two non-terminal nodes is represented by the label on the edge. One node may have multiple parents, among which one is annotated as the primary parent, marked by solid line edges, and others as remote parents, marked by dashed line edges. The primary edges form a tree structure, whereas the remote edges enable reentrancy, forming directed acyclic graphs (DAGs).1 The second feature of UCCA is the existence of nodes with discontinuous leaves, known as discontinuity. For example, node 3 in Figure 1 is discontinuous because some terminal nodes it spans are not its descendants. Hershcovich et al. (2017) first propose a transition-based UCCA Parser, which is used as the baseline in the closed tracks of this shared task. Based on the recent progress on transition- based parsing techniques, they propose a novel set of transition actions to handle both discontinuous and remote nodes and design useful features based on bidirectional LSTMs. Hershcovich et al. (2018) then extend their previous approach and propose to utilize the annotated data with other 1The full UCCA scheme …

Content truncated to 500 words