Abstract
We study the Maximum Subgraph problem in deep dependency parsing. We consider two restrictions to deep dependency graphs: (a) 1-endpoint-crossing and (b) pagenumber-2. Our main contribution is an exact algorithm that obtains maximum subgraphs satisfying both restrictions simultaneously in time O(n5). Moreover, ignoring one linguistically-rare structure descreases the complexity to O(n4). We also extend our quartic-time algorithm into a practical parser with a discriminative disambiguation model and evaluate its performance on four linguistic data sets used in semantic dependency parsing.
Highlights
Dependency parsing has long been studied as a central issue in developing syntactic or semantic analysis
Some linguistic projects grounded on deep grammar formalisms, including Combinatory Categorial Grammar (CCG), LFG, and HPSG, draw attentions to rich syntactic and semantic dependency annotations that are not limited to trees (Hockenmaier and Steedman, 2007; Sun et al, 2014; Ivanova et al, 2012)
We evaluate the coverage of our algorithms on four linguistic data sets: CCGBank, DeepBank, Enju HPSGBank and Prague Dependency TreeBank
Summary
Dependency parsing has long been studied as a central issue in developing syntactic or semantic analysis. Some linguistic projects grounded on deep grammar formalisms, including CCG, LFG, and HPSG, draw attentions to rich syntactic and semantic dependency annotations that are not limited to trees (Hockenmaier and Steedman, 2007; Sun et al, 2014; Ivanova et al, 2012). Parsing for these deep dependency representations can be viewed as the search for Maximum Subgraphs (Kuhlmann and Jonsson, 2015). We will show that relatively satisfactory coverage and parsing complexity can be obtained for graphs that satisfy both restrictions
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have