Results 1  10
of
24
Nonprojective dependency parsing using spanning tree algorithms
 In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing
, 2005
"... 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 natura ..."
Abstract

Cited by 377 (10 self)
 Add to MetaCart
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 nonprojective parsing using ChuLiuEdmonds (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 largemargin learning techniques (Crammer et al., 2003; McDonald et al., 2005) and show that MST parsing increases efficiency and accuracy for languages with nonprojective dependencies. 1
Towards Compressing Web Graphs
 In Proc. of the IEEE Data Compression Conference (DCC
, 2000
"... In this paper, we consider the problem of compressing graphs of the link structure of the World Wide Web. We provide efficient algorithms for such compression that are motivated by recently proposed random graph models for describing the Web. ..."
Abstract

Cited by 104 (1 self)
 Add to MetaCart
In this paper, we consider the problem of compressing graphs of the link structure of the World Wide Web. We provide efficient algorithms for such compression that are motivated by recently proposed random graph models for describing the Web.
Dependency parsing by belief propagation
 In Proceedings of EMNLP
, 2008
"... We formulate dependency parsing as a graphical model with the novel ingredient of global constraints. We show how to apply loopy belief propagation (BP), a simple and effective tool for approximate learning and inference. As a parsing algorithm, BP is both asymptotically and empirically efficient. E ..."
Abstract

Cited by 85 (9 self)
 Add to MetaCart
(Show Context)
We formulate dependency parsing as a graphical model with the novel ingredient of global constraints. We show how to apply loopy belief propagation (BP), a simple and effective tool for approximate learning and inference. As a parsing algorithm, BP is both asymptotically and empirically efficient. Even with secondorder features or latent variables, which would make exact parsing considerably slower or NPhard, BP needs only O(n3) time with a small constant factor. Furthermore, such features significantly improve parse accuracy over exact firstorder methods. Incorporating additional features would increase the runtime additively rather than multiplicatively. 1
Concise Integer Linear Programming Formulations for Dependency Parsing
, 2009
"... We formulate the problem of nonprojective dependency parsing as a polynomialsized integer linear program. Our formulation is able to handle nonlocal output features in an efficient manner; not only is it compatible with prior knowledge encoded as hard constraints, it can also learn soft constraint ..."
Abstract

Cited by 56 (9 self)
 Add to MetaCart
We formulate the problem of nonprojective dependency parsing as a polynomialsized integer linear program. Our formulation is able to handle nonlocal output features in an efficient manner; not only is it compatible with prior knowledge encoded as hard constraints, it can also learn soft constraints from data. In particular, our model is able to learn correlations among neighboring arcs (siblings and grandparents), word valency, and tendencies toward nearlyprojective parses. The model parameters are learned in a maxmargin framework by employing a linear programming relaxation. We evaluate the performance of our parser on data in several natural languages, achieving improvements over existing stateoftheart methods.
Gathering Correlated Data in Sensor Networks
 In Proc. ACM Joint Workshop on Foundations of Mobile Computing (DIALMPOMC
, 2004
"... In this paper, we consider energyefficient gathering of correlated data in sensor networks. We focus on singleinput coding strategies in order to aggregate correlated data. For foreign coding we propose the MEGA algorithm which yields a minimumenergy data gathering topology in O ( n 3) time. We a ..."
Abstract

Cited by 36 (3 self)
 Add to MetaCart
In this paper, we consider energyefficient gathering of correlated data in sensor networks. We focus on singleinput coding strategies in order to aggregate correlated data. For foreign coding we propose the MEGA algorithm which yields a minimumenergy data gathering topology in O ( n 3) time. We also consider selfcoding for which the problem of finding an optimal data gathering tree was recently shown to be NPcomplete; with LEGA, we present the first approximation algorithm for this problem with approximation ratio 2(1 + √ 2) and running time O(m + n log n). Categories and Subject Descriptors:
Face detection by aggregated Bayesian network classifiers
 Pattern Recognition Letters
, 2001
"... A face detection system is presented. A new classi cation method using foreststructured Bayesian networks is used. The method is used in an aggregated classi er to discriminate face from nonface patterns. The process of generating nonface patterns is integrated with the construction of the aggrega ..."
Abstract

Cited by 27 (5 self)
 Add to MetaCart
A face detection system is presented. A new classi cation method using foreststructured Bayesian networks is used. The method is used in an aggregated classi er to discriminate face from nonface patterns. The process of generating nonface patterns is integrated with the construction of the aggregated classi er. The face detection system performs well in comparison with other wellknown methods.
QuadraticTime Dependency Parsing for Machine Translation
"... Efficiency is a prime concern in syntactic MT decoding, yet significant developments in statistical parsing with respect to asymptotic efficiency haven’t yet been explored in MT. Recently, McDonald et al. (2005b) formalized dependency parsing as a maximum spanning tree (MST) problem, which can be so ..."
Abstract

Cited by 11 (1 self)
 Add to MetaCart
Efficiency is a prime concern in syntactic MT decoding, yet significant developments in statistical parsing with respect to asymptotic efficiency haven’t yet been explored in MT. Recently, McDonald et al. (2005b) formalized dependency parsing as a maximum spanning tree (MST) problem, which can be solved in quadratic time relative to the length of the sentence. They show that MST parsing is almost as accurate as cubictime dependency parsing in the case of English, and that it is more accurate with free word order languages. This paper applies MST parsing to MT, and describes how it can be integrated into a phrasebased decoder to compute dependency language model scores. Our results show that augmenting a stateoftheart phrasebased system with this dependency language model leads to significant improvements in TER (0.92%) and BLEU (0.45%) scores on five NIST ChineseEnglish evaluation test sets. 1
Routing explicit side information for data compression in wireless sensor networks
 In DCOSS
, 2005
"... Abstract. Two difficulties in designing datacentric routes [2–5] in wireless sensor networks are the lack of reasonably practical data aggregation models and the high computational complexity resulting from the coupling of routing and innetwork data fusion. In this paper, we study combined routi ..."
Abstract

Cited by 11 (0 self)
 Add to MetaCart
(Show Context)
Abstract. Two difficulties in designing datacentric routes [2–5] in wireless sensor networks are the lack of reasonably practical data aggregation models and the high computational complexity resulting from the coupling of routing and innetwork data fusion. In this paper, we study combined routing and source coding with explicit side information in wireless sensor networks. Our data aggregation model is built upon the observation that in many physical situations the side information that provides the most coding gain comes from a small number of nearby sensors. Based on this model, we propose a routing strategy that separately routes the explicit side information to achieve data compression and cost minimization. The overall optimization problem is NP hard since it has the minimum Steiner tree as a subproblem. We propose a suboptimal algorithm based on maximum weight branching and the shortest path heuristic for the Steiner tree problem. The worst case and average performances of the algorithm are studied through analysis and simulation. 1
Inferring (Biological) Signal Transduction Networks via Transitive Reductions of Directed Graphs
, 2007
"... In this paper we consider the pary transitive reduction (TRp) problem where p>0 is an integer; for p = 2 this problem arises in inferring a sparsest possible (biological) signal transduction network consistent with a set of experimental observations with a goal to minimize false positive infere ..."
Abstract

Cited by 11 (8 self)
 Add to MetaCart
In this paper we consider the pary transitive reduction (TRp) problem where p>0 is an integer; for p = 2 this problem arises in inferring a sparsest possible (biological) signal transduction network consistent with a set of experimental observations with a goal to minimize false positive inferences even if risking false negatives. Special cases of TRp have been investigated before in different contexts; the best previous results are as follows: (1) The minimum equivalent digraph problem, that correspond to a special case of TR1 with no critical edges, is known to be MAXSNPhard, admits a polynomial time algorithm with an approximation ratio of 1.617 + ε for any constant ε>0
Structured Learning for Taxonomy Induction with Belief Propagation
"... We present a structured learning approach to inducing hypernym taxonomies using a probabilistic graphical model formulation. Our model incorporates heterogeneous relational evidence about both hypernymy and siblinghood, captured by semantic features based on patterns and statistics from Web ngrams ..."
Abstract

Cited by 4 (1 self)
 Add to MetaCart
(Show Context)
We present a structured learning approach to inducing hypernym taxonomies using a probabilistic graphical model formulation. Our model incorporates heterogeneous relational evidence about both hypernymy and siblinghood, captured by semantic features based on patterns and statistics from Web ngrams and Wikipedia abstracts. For efficient inference over taxonomy structures, we use loopy belief propagation along with a directed spanning tree algorithm for the core hypernymy factor. To train the system, we extract substructures of WordNet and discriminatively learn to reproduce them, using adaptive subgradient stochastic optimization. On the task of reproducing subhierarchies of WordNet, our approach achieves a 51 % error reduction over a chance baseline, including a 15 % error reduction due to the nonhypernymfactored sibling features. On a comparison setup, we find up to 29 % relative error reduction over previous work on ancestor F1. 1