在text2vec包的基础上,给出了一个生成word embedding.The wiki数据的实例,并在此基础上建立了术语共现矩阵(TCM),利用包中提供的手套函数来创建词嵌入。我想为随包提供的电影评论数据构建word嵌入。我的问题是:
这将导致两个评审之间的边界标记同时发生,这是没有意义的。
**vignettes code:**
library(text2vec)
library(readr)
temp <- tempfile()
download.file('http://mattmahoney.net/dc/text8.zip', temp)
wiki <- read_lines(unz(temp, "text8"))
unlink(temp)
# Create iterator over tokens
tokens <- strsplit(wiki, split = " ", fixed = T)
# Create vocabulary. Terms will be unigrams (simple words).
vocab <- create_vocabulary(itoken(tokens))
vocab <- prune_vocabulary(vocab, term_count_min = 5L)
# We provide an iterator to create_vocab_corpus function
it <- itoken(tokens)
# Use our filtered vocabulary
vectorizer <- vocab_vectorizer(vocab,
# don't vectorize input
grow_dtm = FALSE,
# use window of 5 for context words
skip_grams_window = 5L)
tcm <- create_tcm(it, vectorizer)
fit <- glove(tcm = tcm,
word_vectors_size = 50,
x_max = 10, learning_rate = 0.2,
num_iters = 15)我对开发word嵌入感兴趣的数据如下:
library(text2vec)
data("movie_review")发布于 2016-09-15 21:49:20
不,你不需要连接评论。您只需从令牌上的正确迭代器构造tcm:
library(text2vec)
data("movie_review")
tokens = movie_review$review %>% tolower %>% word_tokenizer
it = itoken(tokens)
# create vocabulary
v = create_vocabulary(it) %>%
prune_vocabulary(term_count_min = 5)
# create co-occurrence vectorizer
vectorizer = vocab_vectorizer(v, grow_dtm = F, skip_grams_window = 5)现在我们需要重新初始化(对于稳定的0.3版本)。对于DEV0.4,不需要重新初始化迭代器):
it = itoken(tokens)
tcm = create_tcm(it, vectorizer)Fit模型:
fit <- glove(tcm = tcm,
word_vectors_size = 50,
x_max = 10, learning_rate = 0.2,
num_iters = 15)https://stackoverflow.com/questions/39514941
复制相似问题