Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision | ||
|
courses:rg:2012:longdtreport [2012/03/12 22:49] longdt |
courses:rg:2012:longdtreport [2012/03/12 22:59] (current) longdt |
||
|---|---|---|---|
| Line 24: | Line 24: | ||
| __Sorted Array__ | __Sorted Array__ | ||
| - | + Use n array for n-gram model (array i-th is used for i-gram) | + | |
| - | | + | - Use n array for n-gram model (array i-th is used for i-gram) |
| - | | + | - Each element in array in pair (w,c) |
| - | | + | |
| - | | + | |
| + | - Sort base on w | ||
| Improvement : Implicitly encode W (all n-gram ending with particular word wi are stored -> wasteful. So, maintain another array save the beginning and the end of the range | Improvement : Implicitly encode W (all n-gram ending with particular word wi are stored -> wasteful. So, maintain another array save the beginning and the end of the range | ||
| Line 50: | Line 52: | ||
| the underline reason is only to support binary search | the underline reason is only to support binary search | ||
| - | ==== Conclusion | + | ==== Decoding |
| + | **I. Exploiting Repetitive Queries** | ||
| - | All in all, it was a paper worth reading, well presented, and thoroughly | + | The method use cache to speed up the process |
| - | discussed, bringing useful general ideas as well as interesting details. | + | This simple implementation increase performance of 300% over conventional implementation |
| + | **II. Exploiting Scrolling Queries** | ||
| + | |||
| + | We can quickly form the context encoding of the next query by concatenating new words with saved offset from previous query | ||
| + | |||
| + | ==== Conclusion ==== | ||
| + | In summary, it was a worth reading | ||
| + | discussed. | ||
