pepijnvink
yoxem稍微研究一下，需要
1. 每個字之間的轉換矩陣
2. 第一個字出現的機率矩陣
3. 文字讀哪個音的機率矩陣
但是實務操作不可能列出不可能的發音的資料項目，比如說guá thiànn lí 不可能列出貓這個字的相關矩陣項目值，所以還需要修剪
#馬克夫鏈 #HiddenMarkovModel #隱式馬可夫模型
Marek GluzaMagdalini Zonnios told me about basic #math behind the complexity of computational mechanics on the level of stochastic processes. Optimising the #entropy of an finite state machine ansatz allows to find a minimal model to account for certain processes and get more clarity e.g. in a time series.
Harald SackToday's #ise2023 lecture was focusing on Naive Bayes Classification, POS Tagging, and distributional semantics with Word Embeddings
https://drive.google.com/drive/folders/11Z3_UGQjGONyHyZbj_kIdgT-LglZH4Ob
#nlp #lecture #classification #wordembeddings #languagemodels #word2vec #hiddenMarkovModel #distributionalsemantics @fizise @KIT_Karlsruhe #stablediffusionart #creativeAI
