Sciweavers

ACL
2009
13 years 9 months ago
K-Best A* Parsing
A parsing makes 1-best search efficient by suppressing unlikely 1-best items. Existing kbest extraction methods can efficiently search for top derivations, but only after an exhau...
Adam Pauls, Dan Klein
ACL
2009
13 years 9 months ago
Unsupervised Learning of Narrative Schemas and their Participants
We describe an unsupervised system for learning narrative schemas, coherent sequences or sets of events (arrested(POLICE,SUSPECT), convicted( JUDGE, SUSPECT)) whose arguments are ...
Nathanael Chambers, Dan Jurafsky
ACL
2009
13 years 9 months ago
Word or Phrase? Learning Which Unit to Stress for Information Retrieval
The use of phrases in retrieval models has been proven to be helpful in the literature, but no particular research addresses the problem of discriminating phrases that are likely ...
Young-In Song, Jung-Tae Lee, Hae-Chang Rim
ACL
2009
13 years 9 months ago
Capturing Salience with a Trainable Cache Model for Zero-anaphora Resolution
This paper explores how to apply the notion of caching introduced by Walker (1996) to the task of zero-anaphora resolution. We propose a machine learning-based implementation of a...
Ryu Iida, Kentaro Inui, Yuji Matsumoto
ACL
2009
13 years 9 months ago
DEPEVAL(summ): Dependency-based Evaluation for Automatic Summaries
This paper presents DEPEVAL(summ), a dependency-based metric for automatic evaluation of summaries. Using a reranking parser and a Lexical-Functional Grammar (LFG) annotation, we ...
Karolina Owczarzak
ACL
2009
13 years 9 months ago
Exploiting Bilingual Information to Improve Web Search
Web search quality can vary widely across languages, even for the same information need. We propose to exploit this variation in quality by learning a ranking function on bilingua...
Wei Gao, John Blitzer, Ming Zhou, Kam-Fai Wong
ACL
2009
13 years 9 months ago
Learning Context-Dependent Mappings from Sentences to Logical Form
We consider the problem of learning context-dependent mappings from sentences to logical form. The training examples are sequences of sentences annotated with lambda-calculus mean...
Luke S. Zettlemoyer, Michael Collins
ACL
2009
13 years 9 months ago
Incremental HMM Alignment for MT System Combination
Inspired by the incremental TER alignment, we re-designed the Indirect HMM (IHMM) alignment, which is one of the best hypothesis alignment methods for conventional MT system combi...
Chi-Ho Li, Xiaodong He, Yupeng Liu, Ning Xi
ACL
2009
13 years 9 months ago
Bayesian Unsupervised Word Segmentation with Nested Pitman-Yor Language Modeling
In this paper, we propose a new Bayesian model for fully unsupervised word segmentation and an efficient blocked Gibbs sampler combined with dynamic programming for inference. Our...
Daichi Mochihashi, Takeshi Yamada, Naonori Ueda
ACL
2009
13 years 9 months ago
The Chinese Aspect Generation Based on Aspect Selection Functions
This paper describes our system for generating Chinese aspect expressions. In the system, the semantics of different aspects is characterized by specific temporal and conceptual f...
Guowen Yang, John A. Bateman