Non-projective dependency parsing using spanning tree algorithms

Non-projective dependency parsing using spanning tree algorithms (2005)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Ryan Mcdonald , Fernando Pereira , Kiril Ribarov , Jan Hajič

Venue:	In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing
Citations:	177 - 9 self

BibTeX

@INPROCEEDINGS{Mcdonald05non-projectivedependency,
    author = {Ryan Mcdonald and Fernando Pereira and Kiril Ribarov and Jan Hajič},
    title = {Non-projective dependency parsing using spanning tree algorithms},
    booktitle = {In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing},
    year = {2005},
    pages = {523--530}
}

Years of Citing Articles

Bookmark

OpenURL

Abstract

We formalize weighted dependency parsing as searching for maximum spanning trees (MSTs) in directed graphs. Using this representation, the parsing algorithm of Eisner (1996) is sufficient for searching over all projective trees in O(n 3) time. More surprisingly, the representation is extended naturally to non-projective parsing using Chu-Liu-Edmonds (Chu and Liu, 1965; Edmonds, 1967) MST algorithm, yielding an O(n 2) parsing algorithm. We evaluate these methods on the Prague Dependency Treebank using online large-margin learning techniques (Crammer et al., 2003; McDonald et al., 2005) and show that MST parsing increases efficiency and accuracy for languages with non-projective dependencies. 1

Citations

7321	Introduction to Algorithms - Cormen, Leiserson, et al. - 2001
1654	B.: Building a large annotated corpus of english: The Penn treebank - Marcus, Marcinkiewicz, et al. - 1993
315	BMaximum-margin Markov networks - Taskar, Guestrin, et al. - 2003
200	Three New Probabilistic Models for Dependency Parsing: An Exploration - Eisner - 1996
175	Ultraconservative online algorithms for multiclass problems - Crammer, Singer - 2003
156	Online large-margin training of dependency parsers - McDonald, Crammer, et al. - 2005
153	Inductive Dependency Parsing - Nivre - 2006
136	Optimum Branchings - Edmonds - 1967
132	Dependency tree kernels for relation extraction - Culotta, Soresen
114	Building a Syntactically Annotated Corpus: The Prague Dependency Treebank - Hajič - 1998
114	Max-margin parsing - Taskar, Klein, et al. - 2004
107	Learning syntactic patterns for automatic hypernym discovery - Snow, Jurafsky, et al. - 2005
100	A Statistical Parser for Czech - Collins, Ramshaw, et al. - 1999
83	Statistical dependency analysis with support vector machines - Yamada, Matsumoto - 2003
76	On the shortest arborescence of a directed graph - Chu, Liu - 1965
72	Deterministic Dependency Parsing of English Text - Nivre, Scholz - 2004
59	Automatic paraphrase acquisition from news articles - Shinyama, Sekine, et al. - 2002
51	Online Passive Aggressive Algorithms - Crammer, Dekel, et al.
51	Machine translation using probabilistic synchronous dependency insertion grammars - Ding, Palmer - 2005
28	Learning and robust learning of product distributions - Höffgen - 1993
16	A statistical constraint dependency grammar (CDG) parser - Wang, Harper - 2004
15	Finding Optimum Branchings. Networks - Tarjan - 1977
5	Arborescence optimization problems solvable by edmonds algorithm - Leonidas - 2003
3	New large margin algorithms for structured prediction - Crammer, McDonald, et al. - 2004
3	Semantic dependency analysis method for Japanese based on optimum tree search algorithm - Hirakawa - 2001
3	The Prague Dependency Treebank 1.0 CDROM. Linguistics Data Consortium Cat - Hajič, Hajicova, et al. - 2001
2	Algorithm for finding the first k shortest arborescences of a digraph - Hou - 1996