Sciweavers

COLING
2008
13 years 6 months ago
Emotion Classification Using Massive Examples Extracted from the Web
In this paper, we propose a data-oriented method for inferring the emotion of a speaker conversing with a dialog system from the semantic content of an utterance. We first fully a...
Ryoko Tokhisa, Kentaro Inui, Yuji Matsumoto
COLING
2008
13 years 6 months ago
Mind the Gap: Dangers of Divorcing Evaluations of Summary Content from Linguistic Quality
In this paper, we analyze the state of current human and automatic evaluation of topic-focused summarization in the Document Understanding Conference main task for 2005-2007. The ...
John M. Conroy, Hoa Trang Dang
COLING
2008
13 years 6 months ago
Shift-Reduce Dependency DAG Parsing
Most data-driven dependency parsing approaches assume that sentence structure is represented as trees. Although trees have several desirable properties from both computational and...
Kenji Sagae, Jun-ichi Tsujii
COLING
2008
13 years 6 months ago
A Systematic Comparison of Phrase-Based, Hierarchical and Syntax-Augmented Statistical MT
Probabilistic synchronous context-free grammar (PSCFG) translation models define weighted transduction rules that represent translation and reordering operations via nonterminal s...
Andreas Zollmann, Ashish Venugopal, Franz Josef Oc...
COLING
2008
13 years 6 months ago
Extractive Summarization Using Supervised and Semi-Supervised Learning
It is difficult to identify sentence importance from a single point of view. In this paper, we propose a learning-based approach to combine various sentence features. They are cat...
Kam-Fai Wong, Mingli Wu, Wenjie Li
COLING
2008
13 years 6 months ago
When is Self-Training Effective for Parsing?
Self-training has been shown capable of improving on state-of-the-art parser performance (McClosky et al., 2006) despite the conventional wisdom on the matter and several studies ...
David McClosky, Eugene Charniak, Mark Johnson
COLING
2008
13 years 6 months ago
Using Three Way Data for Word Sense Discrimination
In this paper, an extension of a dimensionality reduction algorithm called NONNEGATIVE MATRIX FACTORIZATION is presented that combines both `bag of words' data and syntactic ...
Tim Van de Cruys
COLING
2008
13 years 6 months ago
From Words to Senses: A Case Study of Subjectivity Recognition
We determine the subjectivity of word senses. To avoid costly annotation, we evaluate how useful existing resources established in opinion mining are for this task. We show that r...
Fangzhong Su, Katja Markert