论文标题
分析手套模型中加权功能对成本函数的影响
Analyze the Effects of Weighting Functions on Cost Function in the Glove Model
论文作者
论文摘要
在处理较大的词汇尺寸和语料库大小时,训练手套型号的运行时间很长,甚至可以达到数十个小时的数据,大约为500MB。结果,查找加权功能的最佳参数并为弱硬件带来了许多困难。当然,要获得最佳结果,我们需要多次测试基准测试。为了解决此问题,我们得出了一个加权功能,可以节省选择参数和制作基准的时间。它还允许在同一给定时间获得几乎相似的精度,而无需进行实验。
When dealing with the large vocabulary size and corpus size, the run-time for training Glove model is long, it can even be up to several dozen hours for data, which is approximately 500MB in size. As a result, finding and selecting the optimal parameters for the weighting function create many difficulties for weak hardware. Of course, to get the best results, we need to test benchmarks many times. In order to solve this problem, we derive a weighting function, which can save time for choosing parameters and making benchmarks. It also allows one to obtain nearly similar accuracy at the same given time without concern for experimentation.