Sciweavers

ACL
2009
13 years 2 months ago
A Unified Single Scan Algorithm for Japanese Base Phrase Chunking and Dependency Parsing
We describe an algorithm for Japanese analysis that does both base phrase chunking and dependency parsing simultaneously in linear-time with a single scan of a sentence. In this p...
Manabu Sassano, Sadao Kurohashi
ACL
2009
13 years 2 months ago
Parsing Speech Repair without Specialized Grammar Symbols
This paper describes a parsing model for speech with repairs that makes a clear separation between linguistically meaningful symbols in the grammar and operations specific to spee...
Tim Miller, Luan Nguyen, William Schuler
ACL
2009
13 years 2 months ago
Query-Focused Summaries or Query-Biased Summaries?
In the context of the Document Understanding Conferences, the task of Query-Focused Multi-Document Summarization is intended to improve agreement in content among humangenerated m...
Rahul Katragadda, Vasudeva Varma
ACL
2009
13 years 2 months ago
Do Automatic Annotation Techniques Have Any Impact on Supervised Complex Question Answering?
In this paper, we analyze the impact of different automatic annotation methods on the performance of supervised approaches to the complex question answering problem (defined in th...
Yllias Chali, Sadid A. Hasan, Shafiq R. Joty
ACL
2009
13 years 2 months ago
Variational Inference for Grammar Induction with Prior Knowledge
Variational EM has become a popular technique in probabilistic NLP with hidden variables. Commonly, for computational tractability, we make strong independence assumptions, such a...
Shay B. Cohen, Noah A. Smith
ACL
2009
13 years 2 months ago
Generalizing Dependency Features for Opinion Mining
We explore how features based on syntactic dependency relations can be utilized to improve performance on opinion mining. Using a transformation of dependency relation triples, we...
Mahesh Joshi, Carolyn Penstein Rosé
ACL
2009
13 years 2 months ago
Modeling Morphologically Rich Languages Using Split Words and Unstructured Dependencies
We experiment with splitting words into their stem and suffix components for modeling morphologically rich languages. We show that using a morphological analyzer and disambiguator...
Deniz Yuret, Ergun Biçici