facebook - 指定 Facebook fasttext 中 Conceal 单元的数量

Question

在 paper on fasttext对于监督分类，作者通过改变一些参数来指定不同数量的 Conceal 单元(h 是第 3,4 页上的那个 - 在表 1 中您可以看到“它有 10 个 Conceal 单元，我们使用或不使用二元组来评估它。”)但是读完the documentation似乎没有“Conceal 单元”参数需要更改。有没有办法指定 Conceal 单元的数量？或者这与指定 -dim 选项相同吗？

Answer 1

k 是编号。类

摘自 https://arxiv.org/pdf/1607.01759v3.pdf 的第 2.1 节

More precisely, the computational complexity is O(kh) where k is the number of classes and h the dimension of the text representation.

<小时/>

在文本分类中预测类别时，来自 docs :

The argument k is optional, and is equal to 1 by default. In order to obtain the k most likely labels for a piece of text, use:

$ ./fasttext predict model.bin test.txt k

<小时/>

训练模型时，这是在使用 __label__* 标签执行监督训练时在训练数据中隐式指定的。

来自example tutorial :

$ wget https://s3-us-west-1.amazonaws.com/fasttext-vectors/cooking.stackexchange.tar.gz && tar xvzf cooking.stackexchange.tar.gz
--2017-05-23 09:03:26--  https://s3-us-west-1.amazonaws.com/fasttext-vectors/cooking.stackexchange.tar.gz
Resolving s3-us-west-1.amazonaws.com... 54.231.236.45
Connecting to s3-us-west-1.amazonaws.com|54.231.236.45|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 457609 (447K) [application/x-gzip]
Saving to: ‘cooking.stackexchange.tar.gz.1’

cooking.stackexchange.tar.gz.1      100%[================================================================>] 446.88K   385KB/s    in 1.2s    

2017-05-23 09:03:28 (385 KB/s) - ‘cooking.stackexchange.tar.gz.1’ saved [457609/457609]

x cooking.stackexchange.id
x cooking.stackexchange.txt
x readme.txt


$ cat readme.txt 
The data in this archive is derived from the user-contributed content on the
Cooking Stack Exchange website (https://cooking.stackexchange.com/), used under
CC-BY-SA 3.0 (http://creativecommons.org/licenses/by-sa/3.0/).

The original data dump can be downloaded from:
https://archive.org/download/stackexchange/cooking.stackexchange.com.7z
and details about the dump obtained from:
https://archive.org/details/stackexchange

We distribute two files, under CC-BY-SA 3.0:

 - cooking.stackexchange.txt, which contains all question titles and
   their associated tags (one question per line, tags are prefixed by
   the string "__label__") ;

 - cooking.stackexchange.id, which contains the corresponding row IDs,
   from the original data dump.