Sciweavers

37 search results - page 2 / 8
» Non-Projective Dependency Parsing in Expected Linear Time
Sort
View
ECML
2006
Springer
13 years 8 months ago
Efficient Convolution Kernels for Dependency and Constituent Syntactic Trees
In this paper, we provide a study on the use of tree kernels to encode syntactic parsing information in natural language learning. In particular, we propose a new convolution kerne...
Alessandro Moschitti
ACL
2006
13 years 6 months ago
Minimum Risk Annealing for Training Log-Linear Models
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...
David A. Smith, Jason Eisner
CORR
2010
Springer
152views Education» more  CORR 2010»
12 years 11 months ago
Combinatorial Network Optimization with Unknown Variables: Multi-Armed Bandits with Linear Rewards
In the classic multi-armed bandits problem, the goal is to have a policy for dynamically operating arms that each yield stochastic rewards with unknown means. The key metric of int...
Yi Gai, Bhaskar Krishnamachari, Rahul Jain
TRANSCI
2010
101views more  TRANSCI 2010»
13 years 3 months ago
Computing Time-Dependent Bid Prices in Network Revenue Management Problems
We propose a new method to compute bid prices in network revenue management problems. The novel aspect of our method is that it naturally provides dynamic bid prices that depend o...
Sumit Kunnumkal, Huseyin Topaloglu
EMNLP
2010
13 years 2 months ago
Uptraining for Accurate Deterministic Question Parsing
It is well known that parsing accuracies drop significantly on out-of-domain data. What is less known is that some parsers suffer more from domain shifts than others. We show that...
Slav Petrov, Pi-Chuan Chang, Michael Ringgaard, Hi...