Statistical Parsing of Tree Wrapping Grammars

Proceedings of the 28th International Conference on Computational Linguistics, pages 6759–6766 Barcelona, Spain (Online), December 8-13, 2020 6759 Statistical Parsing of Tree Wrapping Grammars Tatiana Bladier Jakub Waszczuk Laura Kallmeyer Heinrich Heine University of Düsseldorf Universitätsstraße 1, 40225 Düsseldorf, Germany {bladier,waszczuk,kallmeyer}@phil.hhu.de Abstract We describe an approach to statistical parsing with Tree-Wrapping Grammars (TWG). TWG is a tree-rewriting formalism which includes the tree-combination operations of substitution, sister- adjunction and tree-wrapping substitution. TWGs can be extracted from constituency treebanks and aim at representing long distance dependencies (LDDs) in a linguistically adequate way. We present a parsing algorithm for TWGs based on neural supertagging and A∗ parsing. We extract a TWG for English from the treebanks for Role and Reference Grammar and discuss first parsing results with this grammar. 1 Introduction We present a statistical parsing approach for Tree-Wrapping Grammar (TWG) (Kallmeyer et al., 2013). TWG is a grammar formalism closely related to Tree-Adjoining Grammar (TAG) (Joshi and Schabes, 1997), which was originally developed with regard to the formalization of the typologically oriented Role and Reference Grammar (RRG) (Van Valin and LaPolla, 1997; Van Valin Jr, 2005). TWG allows for, among others, a more linguistically adequate representation of long distance dependencies (LDDs) in sentences, such as topicalization or long distance wh-movement. In the present paper we show a grammar extraction algorithm for TWG, propose a TWG parser, and discuss parsing results for the grammar extracted from the RRG treebanks RRGbank and RRGparbank1 (Bladier et al., 2018). Similarly to TAG, TWG has the elementary tree combination operations of substitution and sister- adjunction. Additionally, TWG includes the operation of tree-wrapping substitution, which accounts for preserving the connection between the parts of the discontinuous constituents. Operations similar to tree-wrapping substitution were proposed by (Rambow et al., 1995) as subsertion in D-Tree Grammars (DTG) and by (Rambow et al., 2001) as generalized substitution in D-Tree substitution grammar (DSG). To our best knowledge, no statistical parsing approach was proposed for DTG or DSG. An approach to symbolic parsing for TWGs with edge features was proposed in (Arps et al., 2019). In this work, we propose a statistical parsing approach for TWG and extend the pipeline based on supertagging and A∗ algorithm (Waszczuk, 2017; Bladier et al., 2019) originally developed for TAG to be applied to TWG. The contributions of the paper are the following: 1) We present the first approach to statistical parsing for Tree-Wrapping Grammars. 2) We propose an extraction algorithm for TWGs based on the algorithm developed for TAG by (Xia, 1999). 3) We extend and modify the neural A⋆ TAG-parser (Waszczuk, 2017; Kasai et al., 2018; Bladier et al., 2019) to handle the operation of tree-wrapping substitution. 2 Long distance dependencies and wrapping substitution in TWG TWGs consist of elementary trees which can be combined using the operations a) substitution (replacing a leaf node with a tree), b) sister adjunction (adding a new daughter to an internal node) and c) tree-wrapping substitution (adding a tree with a d(ominance)-edge by substituting the lower part of the …

Content truncated to 500 words