Sciweavers

COLING
2008
14 years 1 months ago
Towards Incremental End-of-Utterance Detection in Dialogue Systems
We define the task of incremental or 0lag utterance segmentation, that is, the task of segmenting an ongoing speech recognition stream into utterance units, and present first resu...
Michaela Atterer, Timo Baumann, David Schlangen
COLING
2008
14 years 1 months ago
Phrasal Segmentation Models for Statistical Machine Translation
Phrasal segmentation models define a mapping from the words of a sentence to sequences of translatable phrases. We discuss the estimation of these models from large quantities of ...
Graeme W. Blackwood, Adrià de Gispert, Will...
COLING
2008
14 years 1 months ago
Integrating Motion Predicate Classes with Spatial and Temporal Annotations
We propose a spatio-temporal markup for the annotation of motion predicates in text, informed by a lexical semantic classification of these verbs. We incorporate this classificati...
James Pustejovsky, Jessica L. Moszkowicz
COLING
2008
14 years 1 months ago
A Hybrid Generative/Discriminative Framework to Train a Semantic Parser from an Un-annotated Corpus
We propose a hybrid generative/discriminative framework for semantic parsing which combines the hidden vector state (HVS) model and the hidden Markov support vector machines (HMSV...
Deyu Zhou, Yulan He
COLING
2008
14 years 1 months ago
Evaluating Unsupervised Part-of-Speech Tagging for Grammar Induction
This paper explores the relationship between various measures of unsupervised part-of-speech tag induction and the performance of both supervised and unsupervised parsing models t...
William P. Headden III, David McClosky, Eugene Cha...
COLING
2008
14 years 1 months ago
Modeling Semantic Containment and Exclusion in Natural Language Inference
We propose an approach to natural language inference based on a model of natural logic, which identifies valid inferences by their lexical and syntactic features, without full sem...
Bill MacCartney, Christopher D. Manning
COLING
2008
14 years 1 months ago
Stopping Criteria for Active Learning of Named Entity Recognition
Active learning is a proven method for reducing the cost of creating the training sets that are necessary for statistical NLP. However, there has been little work on stopping crit...
Florian Laws, Hinrich Schütze
COLING
2008
14 years 1 months ago
Automatic Seed Word Selection for Unsupervised Sentiment Classification of Chinese Text
We describe and evaluate a new method of automatic seed word selection for unsupervised sentiment classification of product reviews in Chinese. The whole method is unsupervised an...
Taras Zagibalov, John Carroll