[PYTHON] Convenient goods memo around natural language processing

Machine learning information Collect information

It seems that we need to implement machine learning that handles natural language processing, so I decided to take a look at peripheral services that could be used.

memorandum

・ Rakuten Rapid API (Source: From here) The API I saw for the first time. A collection of APIs from around the world? Looking at the NLP list, it looks like this. Great excellence.

image.png

・ COTOHA API (Source: From here) API created by NTT Communications. The for Developers plan is free and for verification up to 1000 calls / day for each API. The dictionary uses a basic word dictionary. I hope it will be one of the largest dictionaries in Japan.

・ Google Cloud Natural Language (Source: From here) The royal road of GCP. There is a wide range of things you can do. The charge is free for up to 5000 units, with 1000 characters as one unit. Don't pin it. I will buy it for Japanese, but one Japanese character and one English letter are the same one character judgment ...? English seems to be difficult.

image.png

-IBM Cloud (Source: From here and From here -natural-language-classifier))) Free up to 1000 requests per month. Tone Analyzer is an API with great potential, so it looks interesting.

・ Recruit A3RT (Source: From here and From here /)) It seems that the Text Classification API can also build a model on its own. The price is not written, but it is free. .. .. Is it? ?? There seems to be a "typographical error proofreading AI" as another service, which is also anxious. image.png

・ Amazon Comprehend (Source: From here) I didn't understand because the price was buggy, so I wrote down the image for the time being. Is it 1000M characters that 1 unit is 100 characters in 10M units? Is it 0.01 yen? ?? ?? It doesn't seem to support Japanese, so you need to change it to a supported language with Amazon Translate.

image.png

・ Azure Language Understanding (Source: From here) I did some research, but I'm worried that the fee structure seems to be a little annoying. It's the number of transactions. image.png

Thought memo

If you check whether it supports Japanese and how much the fee is, there seems to be no difference in performance for text processing. It is necessary to think variously that audio and video are involved

Recommended Posts

Convenient goods memo around natural language processing
[WIP] Pre-processing memo in natural language processing
Python: Natural language processing
RNN_LSTM2 Natural language processing
Natural language processing 1 Morphological analysis
Natural language processing 3 Word continuity
Study natural language processing with Kikagaku
Natural language processing for busy people
[Natural language processing] Preprocessing with Japanese
Artificial language Lojban and natural language processing (artificial language processing)
Preparing to start natural language processing
Natural language processing analyzer installation summary
3. Natural language processing with Python 2-1. Co-occurrence network
3. Natural language processing with Python 1-1. Word N-gram
I tried natural language processing with transformers.
100 language processing knocks (2020): 40
100 language processing knocks (2020): 32
3. Natural language processing with Python 2-2. Co-occurrence network [mecab-ipadic-NEologd]
100 language processing knocks (2020): 35
100 language processing knocks (2020): 47
100 language processing knocks (2020): 39
100 language processing knocks (2020): 22
100 language processing knocks (2020): 26
100 language processing knocks (2020): 34
100 language processing knocks (2020): 42
100 language processing knocks (2020): 29
100 language processing knocks (2020): 49
100 language processing knocks 06 ~ 09
100 language processing knocks (2020): 43
100 language processing knocks (2020): 24
[Python] I played with natural language processing ~ transformers ~
100 language processing knocks (2020): 45
100 language processing knocks (2020): 10-19
100 language processing knocks (2020): 00-09
100 language processing knocks (2020): 31
100 Language Processing Knock (2020): 38
100 language processing knocks (2020): 48
100 language processing knocks (2020): 44
100 language processing knocks (2020): 41
100 language processing knocks (2020): 37
100 language processing knock 00 ~ 02
100 language processing knocks (2020): 25
Let's enjoy natural language processing with COTOHA API
100 language processing knocks (2020): 23
100 language processing knocks (2020): 33
100 language processing knocks (2020): 20
100 language processing knocks (2020): 27
100 language processing knocks (2020): 46
Unbearable shortness of Attention in natural language processing
100 language processing knocks (2020): 21
100 language processing knocks (2020): 36
Let's enjoy natural language processing with COTOHA API
Bash script memo
100 natural language processing knocks Chapter 4 Morphological analysis (first half)
Set up a development environment for natural language processing
I read an introductory book on natural language processing
100 natural language processing knocks Chapter 1 Preparatory movement (second half)
100 natural language processing knocks Chapter 1 Preparatory movement (first half)
100 natural language processing knocks Chapter 3 Regular expressions (first half)
100 natural language processing knocks Chapter 4 Morphological analysis (second half)
Model using convolutional neural network in natural language processing
3. Natural language processing with Python 4-1. Analysis for words with KWIC