Sciweavers

2929 search results - page 401 / 586
» Models of English Text
Sort
View
KDD
2010
ACM
318views Data Mining» more  KDD 2010»
15 years 3 months ago
DivRank: the interplay of prestige and diversity in information networks
Information networks are widely used to characterize the relationships between data items such as text documents. Many important retrieval and mining tasks rely on ranking the dat...
Qiaozhu Mei, Jian Guo, Dragomir R. Radev
EMNLP
2010
15 years 3 months ago
Translingual Document Representations from Discriminative Projections
Representing documents by vectors that are independent of language enhances machine translation and multilingual text categorization. We use discriminative training to create a pr...
John Platt, Kristina Toutanova, Wen-tau Yih
JAIR
2010
147views more  JAIR 2010»
15 years 8 days ago
Cause Identification from Aviation Safety Incident Reports via Weakly Supervised Semantic Lexicon Construction
The Aviation Safety Reporting System collects voluntarily submitted reports on aviation safety incidents to facilitate research work aiming to reduce such incidents. To effectivel...
Muhammad Arshad Ul Abedin, Vincent Ng, Latifur Kha...
JMLR
2010
137views more  JMLR 2010»
15 years 7 days ago
Covariance in Unsupervised Learning of Probabilistic Grammars
Probabilistic grammars offer great flexibility in modeling discrete sequential data like natural language text. Their symbolic component is amenable to inspection by humans, while...
Shay B. Cohen, Noah A. Smith
ICPR
2000
IEEE
16 years 6 months ago
Extraction of Relevant Information from Document Images Using Measures of Visual Attention
This paper describes an approach to attention based layout segmentation using general principles of the human visual perception to achieve this goal. The text is considered as tex...
Gerd Maderlechner, Angela Schreyer, Peter Suda