Results 1  10
of
10,907
Text Chunking using TransformationBased Learning
, 1995
"... Eric Brill introduced transformationbased learning and showed that it can do partofspeech tagging with fairly high accuracy. The same method can be applied at a higher level of textual interpretation for locating chunks in the tagged text, including nonrecursive "baseNP" chunks. For ..."
Abstract

Cited by 523 (0 self)
 Add to MetaCart
. For this purpose, it is convenient to view chunking as a tagging problem by encoding the chunk structure in new tags attached to each word. In automatic tests using Treebankderived data, this technique achieved recall and precision rates of roughly 92% for baseNP chunks and 88% for somewhat more complex chunks
Precision Rates for Nucleon Weak Interactions in
, 1998
"... We report the results of a detailed calculation of nucleon weak interactions relevant for the neutron to proton density ratio at the onset of primordial nucleosynthesis. Radiative electromagnetic corrections, finite nucleon mass terms, thermal radiative effects on weak processes and on neutrino temp ..."
Abstract
 Add to MetaCart
temperature are taken into account to reduce the theoretical uncertainty on n ↔ p rates to 1%. This translates into a sensitivity in 4 He mass fraction Yp prediction up to 10 −4. We find a positive total correction to the Born prediction δYp ≃ 0.004. PACS number(s): 98.80.Cq; 95.30.Cq; 11.10.Wx; 13.40.Ks 1 1
Precise rates in the law of the iterated logarithm
"... n / log log n). By using the strong approximation, we prove that, if EX2I{X  ≥ t} = o((log log t)−1) as t→∞, then for a> −1 and b> −1, lim ..."
Abstract
 Add to MetaCart
n / log log n). By using the strong approximation, we prove that, if EX2I{X  ≥ t} = o((log log t)−1) as t→∞, then for a> −1 and b> −1, lim
A MaximumEntropyInspired Parser
, 1999
"... We present a new parser for parsing down to Penn treebank style parse trees that achieves 90.1% average precision/recall for sentences of length 40 and less, and 89.5% for sentences of length 100 and less when trained and tested on the previously established [5,9,10,15,17] "stan dard" se ..."
Abstract

Cited by 971 (19 self)
 Add to MetaCart
We present a new parser for parsing down to Penn treebank style parse trees that achieves 90.1% average precision/recall for sentences of length 40 and less, and 89.5% for sentences of length 100 and less when trained and tested on the previously established [5,9,10,15,17] "stan dard
A generalized processor sharing approach to flow control in integrated services networks: The singlenode case
 IEEE/ACM TRANSACTIONS ON NETWORKING
, 1993
"... The problem of allocating network resources to the users of an integrated services network is investigated in the context of ratebased flow control. The network is assumed to be a virtual circuit, connectionbased packet network. We show that the use of Generalized processor Sharing (GPS), when co ..."
Abstract

Cited by 2010 (5 self)
 Add to MetaCart
The problem of allocating network resources to the users of an integrated services network is investigated in the context of ratebased flow control. The network is assumed to be a virtual circuit, connectionbased packet network. We show that the use of Generalized processor Sharing (GPS), when
The Contourlet Transform: An Efficient Directional Multiresolution Image Representation
 IEEE TRANSACTIONS ON IMAGE PROCESSING
"... The limitations of commonly used separable extensions of onedimensional transforms, such as the Fourier and wavelet transforms, in capturing the geometry of image edges are well known. In this paper, we pursue a “true” twodimensional transform that can capture the intrinsic geometrical structure t ..."
Abstract

Cited by 513 (20 self)
 Add to MetaCart
flexible multiresolution, local, and directional image expansion using contour segments, and thus it is named the contourlet transform. The discrete contourlet transform has a fast iterated filter bank algorithm that requires an order N operations for Npixel images. Furthermore, we establish a precise
Loopy belief propagation for approximate inference: An empirical study. In:
 Proceedings of Uncertainty in AI,
, 1999
"... Abstract Recently, researchers have demonstrated that "loopy belief propagation" the use of Pearl's polytree algorithm in a Bayesian network with loops can perform well in the context of errorcorrecting codes. The most dramatic instance of this is the near Shannonlimit performanc ..."
Abstract

Cited by 676 (15 self)
 Add to MetaCart
with a single loop • Unless all the conditional probabilities are deter ministic, belief propagation will converge. • There is an analytic expression relating the cor rect marginals to the loopy marginals. The ap proximation error is related to the convergence rate of the messages the faster
Explicit and precise rate control for wireless sensor networks
 in: Proceedings of the 7th ACM Conference on Embedded Networked Sensor Systems (SenSys
, 2009
"... The state of the art congestion control algorithms for wireless sensor networks respond to coarsegrained feedback regarding available capacity in the network with an additive increase multiplicative decrease mechanism to set source rates. Providing precise feedback is challenging in wireless networ ..."
Abstract

Cited by 18 (4 self)
 Add to MetaCart
The state of the art congestion control algorithms for wireless sensor networks respond to coarsegrained feedback regarding available capacity in the network with an additive increase multiplicative decrease mechanism to set source rates. Providing precise feedback is challenging in wireless
Precise rates in the law of the logarithm in the Hilbert space∗
"... Abstract. Let {X,Xn;n ≥ 1} be a sequence of i.i.d. random variables taking values in a real separable Hilbert space (H, ‖ · ‖) with covariance operator Σ, and set Sn = X1 +...+Xn, n ≥ 1. Let an = o( n / logn). We prove that, for any 1 < r < 3/2 and a> −d/2, lim ε↘√r−1 ε2 − (r − 1)]a+d/2 ∞ ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
Abstract. Let {X,Xn;n ≥ 1} be a sequence of i.i.d. random variables taking values in a real separable Hilbert space (H, ‖ · ‖) with covariance operator Σ, and set Sn = X1 +...+Xn, n ≥ 1. Let an = o( n / logn). We prove that, for any 1 < r < 3/2 and a> −d/2, lim ε↘√r−1 ε2 − (r − 1)]a+d/2 ∞∑ n=1 nr−2(log n)aP ‖Sn ‖ ≥ σφ(n)ε+ an = Γ−1(d/2)K(Σ)(r − 1) d−22 Γ(a+ d/2) holds if EX = 0, E[(X, y)]2 <∞, E[‖X‖2r(log ‖X‖)a−r] <∞, and E[(X, ei)2I{(X, ei) > t}] = o ( 1log t), as t→∞, for ∀i.
Results 1  10
of
10,907