This shows you the differences between two versions of the page.
Next revision | Previous revision | ||
papers:collobert-2011 [2011/10/08 23:01] leonb created |
papers:collobert-2011 [2011/10/08 23:21] (current) leonb [Senna] |
||
---|---|---|---|
Line 21: | Line 21: | ||
Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu and Pavel Kuksa: | Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu and Pavel Kuksa: | ||
+ | [[http:// | ||
+ | < | ||
[[http:// | [[http:// | ||
[[http:// | [[http:// | ||
Line 36: | Line 38: | ||
url = {http:// | url = {http:// | ||
} | } | ||
+ | |||
+ | |||
+ | |||
+ | ==== Senna ==== | ||
+ | |||
+ | The universal natural language tagger described in this paper | ||
+ | is actively maintained by [[http:// | ||
+ | It can be downloaded from [[http:// | ||
+ | Besides part-of-speech tagging, chunking, named entity extraction, and semantic role labelling, | ||
+ | the latest version also outputs syntactic parse trees, still using the neural network architecture described in this paper. | ||
+ | |||
+ | * State-of-the-art or near-state-of-the-art tagging accuracies. | ||
+ | * Exceptional tagging speed (POS+NER+Chunk+SRL+Parse at more than 10000 words per second.) | ||
+ | * Small memory footprint (about 120MB.) | ||
+ | * Compact soure code (about 3000 lines of C.) | ||
+ | |||
+ | |||
+ | |||
+ | |||