Sciweavers

EMNLP
2007
13 years 6 months ago
Phrase Reordering Model Integrating Syntactic Knowledge for SMT
Reordering model is important for the statistical machine translation (SMT). Current phrase-based SMT technologies are good at capturing local reordering but not global reordering...
Dongdong Zhang, Mu Li, Chi-Ho Li, Ming Zhou
EMNLP
2007
13 years 6 months ago
LEDIR: An Unsupervised Algorithm for Learning Directionality of Inference Rules
Semantic inference is a core component of many natural language applications. In response, several researchers have developed algorithms for automatically learning inference rules...
Rahul Bhagat, Patrick Pantel, Eduard H. Hovy
EMNLP
2007
13 years 6 months ago
A Constraint Satisfaction Approach to Dependency Parsing
We present an adaptation of constraint satisfaction inference (Canisius et al., 2006b) for predicting dependency trees. Three different classifiers are trained to predict weighte...
Sander Canisius, Erik Tjong Kim Sang
EMNLP
2007
13 years 6 months ago
Extracting Aspect-Evaluation and Aspect-Of Relations in Opinion Mining
The technology of opinion extraction allows users to retrieve and analyze people’s opinions scattered over Web documents. We define an opinion unit as a quadruple consisting of...
Nozomi Kobayashi, Kentaro Inui, Yuji Matsumoto
EMNLP
2007
13 years 6 months ago
Joint Morphological and Syntactic Disambiguation
In morphologically rich languages, should morphological and syntactic disambiguation be treated sequentially or as a single problem? We describe several efficient, probabilistica...
Shay B. Cohen, Noah A. Smith
EMNLP
2007
13 years 6 months ago
Recovery of Empty Nodes in Parse Structures
In this paper, we describe a new algorithm for recovering WH-trace empty nodes. Our approach combines a set of hand-written patterns together with a probabilistic model. Because t...
Denis Filimonov, Mary P. Harper
EMNLP
2007
13 years 6 months ago
Structural Correspondence Learning for Dependency Parsing
Following (Blitzer et al., 2006), we present an application of structural correspondence learning to non-projective dependency parsing (McDonald et al., 2005). To induce the corre...
Nobuyuki Shimizu, Hiroshi Nakagawa
EMNLP
2007
13 years 6 months ago
Lexical Semantic Relatedness with Random Graph Walks
Many systems for tasks such as question answering, multi-document summarization, and information retrieval need robust numerical measures of lexical relatedness. Standard thesauru...
Thad Hughes, Daniel Ramage
EMNLP
2007
13 years 6 months ago
Probabilistic Models of Nonprojective Dependency Trees
A notable gap in research on statistical dependency parsing is a proper conditional probability distribution over nonprojective dependency trees for a given sentence. We exploit t...
David A. Smith, Noah A. Smith
EMNLP
2007
13 years 6 months ago
Large Margin Synchronous Generation and its Application to Sentence Compression
This paper presents a tree-to-tree transduction method for text rewriting. Our model is based on synchronous tree substitution grammar, a formalism that allows local distortion of...
Trevor Cohn, Mirella Lapata