Sciweavers

637 search results - page 2 / 128
» Collecting Highly Parallel Data for Paraphrase Evaluation
Sort
View
EMNLP
2010
13 years 2 months ago
PEM: A Paraphrase Evaluation Metric Exploiting Parallel Texts
We present PEM, the first fully automatic metric to evaluate the quality of paraphrases, and consequently, that of paraphrase generation systems. Our metric is based on three crit...
Chang Liu, Daniel Dahlmeier, Hwee Tou Ng
EMNLP
2011
12 years 4 months ago
Learning Sentential Paraphrases from Bilingual Parallel Corpora for Text-to-Text Generation
Previous work has shown that high quality phrasal paraphrases can be extracted from bilingual parallel corpora. However, it is not clear whether bitexts are an appropriate resourc...
Juri Ganitkevitch, Chris Callison-Burch, Courtney ...
IWMM
2010
Springer
157views Hardware» more  IWMM 2010»
13 years 9 months ago
Tracing garbage collection on highly parallel platforms
The pervasiveness of multiprocessor and multicore hardware and the rising level of available parallelism are radically changing the computing landscape. Can software deal with tom...
Katherine Barabash, Erez Petrank
CCGRID
2001
IEEE
13 years 8 months ago
TACO-Exploiting Cluster Networks for High-Level Collective Operations
TACO (Topologies and Collections) is a template library that introduces the flavour of distributed data parallel processing by means of reusable topology classes and C++ s. This p...
Jörg Nolte, Mitsuhisa Sato, Yutaka Ishikawa
PDPTA
2010
13 years 2 months ago
Collecting Sensor Data for High-Performance Computing: A Case-study
- Many research questions remain open with regard to improving reliability in exascale systems. Among others, statistics-based analysis has been used to find anomalies, to isolate ...
Line C. Pouchard, Jonathan D. Dobson, Stephen W. P...