Sciweavers

ACL
2008
13 years 9 months ago
Enforcing Transitivity in Coreference Resolution
A desirable quality of a coreference resolution system is the ability to handle transitivity constraints, such that even if it places high likelihood on a particular mention being...
Jenny Rose Finkel, Christopher D. Manning
ACL
2008
13 years 9 months ago
Partial Matching Strategy for Phrase-based Statistical Machine Translation
This paper presents a partial matching strategy for phrase-based statistical machine translation (PBSMT). Source phrases which do not appear in the training corpus can be translat...
Zhongjun He, Qun Liu, Shouxun Lin
ACL
2008
13 years 9 months ago
Mixture Model POMDPs for Efficient Handling of Uncertainty in Dialogue Management
In spoken dialogue systems, Partially Observable Markov Decision Processes (POMDPs) provide a formal framework for making dialogue management decisions under uncertainty, but effi...
James Henderson, Oliver Lemon
ACL
2008
13 years 9 months ago
Simulating the Behaviour of Older versus Younger Users when Interacting with Spoken Dialogue Systems
In this paper we build user simulations of older and younger adults using a corpus of interactions with a Wizard-of-Oz appointment scheduling system. We measure the quality of the...
Kallirroi Georgila, Maria Wolters, Johanna D. Moor...
ACL
2007
13 years 9 months ago
Learning Predictive Structures for Semantic Role Labeling of NomBank
This paper presents a novel application of Alternating Structure Optimization (ASO) to the task of Semantic Role Labeling (SRL) of noun predicates in NomBank. ASO is a recently pr...
Chang Liu, Hwee Tou Ng
ACL
2008
13 years 9 months ago
Active Learning with Confidence
Active learning is a machine learning approach to achieving high-accuracy with a small amount of labels by letting the learning algorithm choose instances to be labeled. Most of p...
Mark Dredze, Koby Crammer
ACL
2008
13 years 9 months ago
Choosing Sense Distinctions for WSD: Psycholinguistic Evidence
Supervised word sense disambiguation requires training corpora that have been tagged with word senses, which begs the question of which word senses to tag with. The default choice...
Susan Windisch Brown
ACL
2007
13 years 9 months ago
A Computational Model of Text Reuse in Ancient Literary Texts
We propose a computational model of text reuse tailored for ancient literary texts, available to us often only in small and noisy samples. The model takes into account source alte...
John Lee
ACL
2008
13 years 9 months ago
Beyond Log-Linear Models: Boosted Minimum Error Rate Training for N-best Re-ranking
Current re-ranking algorithms for machine translation rely on log-linear models, which have the potential problem of underfitting the training data. We present BoostedMERT, a nove...
Kevin Duh, Katrin Kirchhoff