Open Wascien opened 2 years ago
逻辑是这样的:
Reference: [Mikolov et al.2011] Tom´aˇs Mikolov, Anoop Deoras,Daniel Povey, Luk´aˇs Burget, and Jan Cernock`y. 2011. ˇStrategies for training large scale neural network language models. In Workshop on Automatic Speech Recognition and Understanding. IEEE. https://en.wikipedia.org/wiki/Katz%27s_back-off_model
` def biGramHash(sequence, t, buckets): t1 = sequence[t - 1] if t - 1 >= 0 else 0 return (t1 * 14918087) % buckets
我想请问一下,关于n-gram,您在代码中是这样映射过去的。我有点疑惑,比如2-gram,为什么只用了2个单词中的前一个id进行了映射,而不是使用两个单词id?