Sciweavers

10542 search results - page 337 / 2109
» A General Notion of Useful Information
Sort
View
ACL
2004
15 years 8 months ago
Enriching the Output of a Parser Using Memory-based Learning
We describe a method for enriching the output of a parser with information available in a corpus. The method is based on graph rewriting using memorybased learning, applied to dep...
Valentin Jijkoun, Maarten de Rijke
IJIS
2007
155views more  IJIS 2007»
15 years 6 months ago
Clustering web search results using fuzzy ants
Algorithms for clustering web search results have to be efficient and robust. Furthermore they must be able to cluster a dataset without using any kind of a priori information, s...
Steven Schockaert, Martine De Cock, Chris Cornelis...
168
Voted
EMNLP
2007
15 years 8 months ago
Using Semantic Roles to Improve Question Answering
Shallow semantic parsing, the automatic identification and labeling of sentential constituents, has recently received much attention. Our work examines whether semantic role info...
Dan Shen, Mirella Lapata
ACL
2010
15 years 4 months ago
Evaluating Machine Translations Using mNCD
This paper introduces mNCD, a method for automatic evaluation of machine translations. The measure is based on normalized compression distance (NCD), a general information theoret...
Marcus Dobrinkat, Tero Tapiovaara, Jaakko Väy...
SIGIR
2004
ACM
16 years 8 days ago
Usefulness of hyperlink structure for query-biased topic distillation
In this paper, we introduce an information theoretic method for estimating the usefulness of the hyperlink structure induced from the set of retrieved documents. We evaluate the e...
Vassilis Plachouras, Iadh Ounis