Results 1  10
of
20
Incremental integer linear programming for nonprojective dependency parsing
 In EMNLP
, 2006
"... Integer Linear Programming has recently been used for decoding in a number of probabilistic models in order to enforce global constraints. However, in certain applications, such as nonprojective dependency parsing and machine translation, the complete formulation of the decoding problem as an integ ..."
Abstract

Cited by 52 (6 self)
 Add to MetaCart
Integer Linear Programming has recently been used for decoding in a number of probabilistic models in order to enforce global constraints. However, in certain applications, such as nonprojective dependency parsing and machine translation, the complete formulation of the decoding problem as an integer linear program renders solving intractable. We present an approach which solves the problem incrementally, thus we avoid creating intractable integer linear programs. This approach is applied to Dutch dependency parsing and we show how the addition of linguistically motivated constraints can yield a significant improvement over stateoftheart. 1
Dynamic Programming for LinearTime Incremental Parsing
"... Incremental parsing techniques such as shiftreduce have gained popularity thanks to their efficiency, but there remains a major problem: the search is greedy and only explores a tiny fraction of the whole space (even with beam search) as opposed to dynamic programming. We show that, surprisingly, d ..."
Abstract

Cited by 51 (4 self)
 Add to MetaCart
(Show Context)
Incremental parsing techniques such as shiftreduce have gained popularity thanks to their efficiency, but there remains a major problem: the search is greedy and only explores a tiny fraction of the whole space (even with beam search) as opposed to dynamic programming. We show that, surprisingly, dynamic programming is in fact possible for many shiftreduce parsers, by merging “equivalent ” stacks based on feature values. Empirically, our algorithm yields up to a fivefold speedup over a stateoftheart shiftreduce dependency parser with no loss in accuracy. Better search also leads to better learning, and our final parser outperforms all previously reported dependency parsers for English and Chinese, yet is much faster. 1
Constraints on nonprojective dependency parsing
 In Proc. EACL
, 2006
"... An open issue in datadriven dependency parsing is how to handle nonprojective dependencies, which seem to be required by linguistically adequate representations, but which pose problems in parsing with respect to both accuracy and efficiency. Using data from five different languages, we evaluate a ..."
Abstract

Cited by 15 (5 self)
 Add to MetaCart
An open issue in datadriven dependency parsing is how to handle nonprojective dependencies, which seem to be required by linguistically adequate representations, but which pose problems in parsing with respect to both accuracy and efficiency. Using data from five different languages, we evaluate an incremental deterministic parser that derives nonprojective dependency structures in O(n 2) time, supported by SVM classifiers for predicting the next parser action. The experiments show that unrestricted nonprojective parsing gives a significant improvement in accuracy, compared to a strictly projective baseline, with up to 35 % error reduction, leading to stateoftheart results for the given data sets. Moreover, by restricting the class of permissible structures to limited degrees of nonprojectivity, the parsing time can be reduced by up to 50 % without a significant decrease in accuracy. 1
NonProjective Dependency Parsing in Expected Linear Time
"... We present a novel transition system for dependency parsing, which constructs arcs only between adjacent words but can parse arbitrary nonprojective trees by swapping the order of words in the input. Adding the swapping operation changes the time complexity for deterministic parsing from linear to ..."
Abstract

Cited by 11 (3 self)
 Add to MetaCart
We present a novel transition system for dependency parsing, which constructs arcs only between adjacent words but can parse arbitrary nonprojective trees by swapping the order of words in the input. Adding the swapping operation changes the time complexity for deterministic parsing from linear to quadratic in the worst case, but empirical estimates based on treebank data show that the expected running time is in fact linear for the range of data attested in the corpora. Evaluation on data from five languages shows stateoftheart accuracy, with especially good results for the labeled exact match score. 1
A TransitionBased Parser for 2Planar Dependency Structures
"... Finding a class of structures that is rich enough for adequate linguistic representation yet restricted enough for efficient computational processing is an important problem for dependency parsing. In this paper, we present a transition system for 2planar dependency trees – trees that can be decomp ..."
Abstract

Cited by 9 (3 self)
 Add to MetaCart
Finding a class of structures that is rich enough for adequate linguistic representation yet restricted enough for efficient computational processing is an important problem for dependency parsing. In this paper, we present a transition system for 2planar dependency trees – trees that can be decomposed into at most two planar graphs – and show that it can be used to implement a classifierbased parser that runs in linear time and outperforms a stateoftheart transitionbased parser on four data sets from the CoNLLX shared task. In addition, we present an efficient method for determining whether an arbitrary tree is 2planar and show that 99 % or more of the trees in existing treebanks are 2planar. 1
Two Semantic features make all the difference in Parsing accuracy
 In Proc. of ICON2008
, 2008
"... semantic features make all the difference in Parsing accuracy. by ..."
Abstract

Cited by 9 (5 self)
 Add to MetaCart
semantic features make all the difference in Parsing accuracy. by
Dependency Parsing and Projection Based on WordPair Classification
"... In this paper we describe an intuitionistic method for dependency parsing, where a classifier is used to determine whether a pair of words forms a dependency edge. And we also propose an effective strategy for dependency projection, where the dependency relationships of the word pairs in the source ..."
Abstract

Cited by 3 (2 self)
 Add to MetaCart
(Show Context)
In this paper we describe an intuitionistic method for dependency parsing, where a classifier is used to determine whether a pair of words forms a dependency edge. And we also propose an effective strategy for dependency projection, where the dependency relationships of the word pairs in the source language are projected to the word pairs of the target language, leading to a set of classification instances rather than a complete tree. Experiments show that, the classifier trained on the projected classification instances significantly outperforms previous projected dependency parsers. More importantly, when this classifier is integrated into a maximum spanning tree (MST) dependency parser, obvious improvement is obtained over the MST baseline. 1
Branch and bound algorithm for dependency parsing with nonlocal features. TACL
, 2013
"... Graph based dependency parsing is inefficient when handling nonlocal features due to high computational complexity of inference. In this paper, we proposed an exact and efficient decoding algorithm based on the Branch and Bound (B&B) framework where nonlocal features are bounded by a linear com ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
Graph based dependency parsing is inefficient when handling nonlocal features due to high computational complexity of inference. In this paper, we proposed an exact and efficient decoding algorithm based on the Branch and Bound (B&B) framework where nonlocal features are bounded by a linear combination of local features. Dynamic programming is used to search the upper bound. Experiments are conducted on English PTB and Chinese CTB datasets. We achieved competitive Unlabeled Attachment Score (UAS) when no additional resources are available: 93.17% for English and 87.25 % for Chinese. Parsing speed is 177 words per second for English and 97 words per second for Chinese. Our algorithm is general and can be adapted to nonprojective dependency parsing or other graphical models. 1
Dependencybased Discourse Parser for SingleDocument Summarization
"... The current stateoftheart singledocument summarization method generates a summary by solving a Tree Knapsack Problem (TKP), which is the problem of finding the optimal rooted subtree of the dependencybased discourse tree (DEPDT) of a document. We can obtain a gold DEPDT by transforming a go ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
The current stateoftheart singledocument summarization method generates a summary by solving a Tree Knapsack Problem (TKP), which is the problem of finding the optimal rooted subtree of the dependencybased discourse tree (DEPDT) of a document. We can obtain a gold DEPDT by transforming a gold Rhetorical Structure Theorybased discourse tree (RSTDT). However, there is still a large difference between the ROUGE scores of a system with a gold DEPDT and a system with a DEPDT obtained from an automatically parsed RSTDT. To improve the ROUGE score, we propose a novel discourse parser that directly generates the DEPDT. The evaluation results showed that the TKP with our parser outperformed that with the stateoftheart RSTDT parser, and achieved almost equivalent ROUGE scores to the TKP with the gold DEPDT. 1
Textlevel Discourse Dependency Parsing
"... Previous researches on Textlevel discourse parsing mainly made use of constituency structure to parse the whole document into one discourse tree. In this paper, we present the limitations of constituency based discourse parsing and first propose to use dependency structure to directly represent t ..."
Abstract

Cited by 2 (0 self)
 Add to MetaCart
(Show Context)
Previous researches on Textlevel discourse parsing mainly made use of constituency structure to parse the whole document into one discourse tree. In this paper, we present the limitations of constituency based discourse parsing and first propose to use dependency structure to directly represent the relations between elementary discourse units (EDUs). The stateoftheart dependency parsing techniques, the Eisner algorithm and maximum spanning tree (MST) algorithm, are adopted to parse an optimal discourse dependency tree based on the arcfactored model and the largemargin learning techniques. Experiments show that our discourse dependency parsers achieve a competitive performance on textlevel discourse parsing. 1