Left-corner Parsing for Dependency Grammar

Abstract

In this article, we present an incremental dependency parsing algorithm with an arc-eager variant of the left-corner parsing strategy. Our algorithm's stack depth captures the center-embeddedness of the recognized dependency structure. A higher stack depth occurs only when processing deeper center-embedded sentences in which people find difficulty in comprehension. We examine whether our algorithm can capture the syntactic regularity that universally exists in languages through two kinds of experiments across treebanks of 19 languages. We first show through oracle parsing experiments that our parsing algorithm consistently requires less stack depth to recognize annotated trees relative to other algorithms across languages. This result also suggests the existence of a syntactic universal by which deeper center-embedding is a rare construction across languages, a result that has yet to be quantitatively cross-linguistically examined. We further investigate the above claim through supervised parsing experiments and show that our proposed parser is consistently less sensitive to constraints on stack depth bounds when decoding across languages, while the performance of other parsers such as the arc-eager parser is largely affected by such constraints. We thus conclude that the stack depth of our parser represents a more meaningful measure for capturing syntactic regularity in languages than those of existing parsers. IntroductionMany parsing algorithms in computational linguistics can be formalized as a manipulation of elements on a stack. For example, the shift-reduce algorithm constructs a parse tree by combining subtrees on the stack in a bottom-up manner. In general, the stack preserves disjoint elements (e.g., unconnected subtrees) and the parser constructs a parse tree by combining those subtrees in a parser-specific manner.Here, we focus on an instance of stack-based algorithms called arc-eager left-corner parsing 1 † National Institute of Informatics † † SOKENDAI (The Graduate University for Advanced Studies) 1 There are two types of left-corner parsing, namely arc-standard and arc-eager. Since we only focus on arceager left-corner parsing, we refer to left-corner parsing as the arc-eager algorithm in this article. Note that these terms (i.e., arc-standard and arc-eager) are also used as the names of dependency parsing algorithms (transition system) (Nivre 2008), but they are not relevant with one another.

Second-Order Unsupervised Neural Dependency Parsing

“…In Figure 4, we find DMO converges faster than EM and converges to a higher log-likelihood. In Figure 4, we find that the model accuracy of DMO is much higher than that of EM at (Noji and Miyao, 2015). DV,VV:…”

Efficiency Analysis of Deeplearning4J Neural Network Classifiers in Development of Transition Based Dependency Parsers

“…In the literature, we can find only a few experiments where some Hungarian corpus was also among the examined languages. Noji (2016) used pseudo-projective dependency parsing to process the non-projective language formulas [19]. For Hungarian they achieved 80,9% UAS with arc-eager and 79,1% with arc-standard algorithms.…”

An Exploration of Left-Corner Transformations

“…Moreover, statistical left-corner parsers have proven themselves empirically effective for several grammar formalisms (Roark andJohnson, 1999; Roark, 2001;Díaz et al, 2002;Noji and Miyao, 2014;Noji et al, 2016; Shain et al, 2016; Stanojević and Stabler, 2018;Kitaev and Klein, 2020).…”