今回作るものはタイトル通り日本語学習済みモデルのBERTを実装し、文章ないの単語の重要度を取得することである。
下記の環境で行った。homebrewやpipの環境はあるものとして進める。

環境

mac OS
Homebrew           4.2.8
Python             3.9.6
pip                24.0
transformers       4.37.2
tokenizers         0.15.2
torch              2.2.0

環境構築

初めに今回使用するモデルを使うための環境構築とモデルのデータを用意する。

Juman++

Juman++のインストールを行う。
インストールは下記のページを参照した。
https://qiita.com/TakayoshiK/items/2fed43b2ed4e6433ab1b

$ brew install jumanpp
$ brew tap uetchy/nlp
$ brew install knp

BERT日本語モデル(京都大学　黒橋・河原・村脇研究室)

参照ページ
https://toukei-lab.com/bert
次に、BERTの日本語モデル(京都大学　黒橋・河原・村脇研究室)データを持ってくる。
下記のURL内の好きなモデルをダンロードする。今回このページでは" Japanese_L-24_H-1024_A-16_E-30_BPE_WWM.zip"を用いた。
https://nlp.ist.i.kyoto-u.ac.jp/index.php?ku_bert_japanese
ダンロード後好きな位置で解答する。今回は仮に"japanese_model"フォルダーの中に解凍したとする。

パソコンが重くなって嫌だ解凍したくないという人にはGoogleDriveをマウントする方法をおすすめする。(参照ページに記載)

ライセンスに関すること

今回、BERTの日本語モデル(京都大学　黒橋・河原・村脇研究室)様の開発したBERTモデルを使用し、記事を書かせていただくことに深く感謝いたします。下記にライセンスに関する全文を記載いたします。
https://www.apache.org/licenses/LICENSE-2.0
---------------------------------------------------------------------------------------------
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/

TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION

Definitions.

"License" shall mean the terms and conditions for use, reproduction, and distribution as defined by Sections 1 through 9 of this document.

"Licensor" shall mean the copyright owner or entity authorized by the copyright owner that is granting the License.

"Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity.

"You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License.

"Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files.

"Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types.

"Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work (an example is provided in the Appendix below).

"Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof.

"Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution."

"Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work.

Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form.
Grant of Patent License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed.
Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions:

You must give any other recipients of the Work or Derivative Works a copy of this License; and
You must cause any modified files to carry prominent notices stating that You changed the files; and
You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and
If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License.
You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License.

Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions.
Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except as required for reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file.
Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License.
Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages.
Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability.

END OF TERMS AND CONDITIONS
---------------------------------------------------------------------------------------------

必要ライブラリの準備

transformersなどを入れる。

$ pip3 install transformers
$ pip3 install torch

transformersを入れたが
ImportError: urllib3 v2.0 only supports OpenSSL 1.1.1+, currently the 'ssl' module is compiled with LibreSSL 2.8.3. See: https://github.com/urllib3/urllib3/issues/2168
のエラーが出る人(主もハマりました。)下記のページ参照
https://stackoverflow.com/questions/76187256/importerror-urllib3-v2-0-only-supports-openssl-1-1-1-currently-the-ssl-modu

$ pip3 uninstall urllib3
$ pip3 install 'urllib3<2.0'

のダウングレードで実行できました。

プログラム作成

ここまできたらもう後は一瞬プログラムを作れば良いだけだ!
今までのサイトを参照しつつ...

vector_words.py

import torch
from transformers import BertTokenizer, BertModel, BertConfig
from pyknp import Juman
jumanpp = Juman()

config = BertConfig.from_json_file('./Japanese_L-24_H/bert_config.json')

model = BertModel.from_pretrained('./Japanese_L-24_H/pytorch_model.bin',config=config)
bert_tokenizer = BertTokenizer('./Japanese_L-24_H/vocab.txt', do_lower_case = False, do_basic_tokenize = False)

print("テキストを入力して下さい。")
text = input()

# jumanppを用いて分解
token_text = jumanpp.analysis(text)
tokenized_text = [mrph.midasi for mrph in token_text.mrph_list()]

# BERTで扱えるように変換
tokens = bert_tokenizer.convert_tokens_to_ids(tokenized_text)
tokens_tensor = torch.tensor([tokens])

# BERTモデルで特徴ベクトルを取得
with torch.no_grad():
    outputs = model(tokens_tensor)
    attention = outputs.last_hidden_state

# 特徴量の総和が1になるように
word_importance = attention.sum(dim=1).squeeze()

# 単語とその重要度を対応付けたリストを作成
word_importance_list = [(token, importance) for token, importance in zip(tokenized_text, word_importance)]

# 重要度が高い順にソート
sorted_word_importance_list = sorted(word_importance_list, key=lambda x: x[1], reverse=True)

# 重要度の高い順に単語と重要度を出力
for token, importance in sorted_word_importance_list:
    print(f"単語: {token}, 重要度: {importance}")

さてさて、実行してみると...

$ python3 vector_words.py
テキストを入力して下さい。
私はPythonを勉強しています。
単語: ます, 重要度: 4.842738151550293
単語: 勉強, 重要度: 4.570006370544434
単語: を, 重要度: 3.3558690547943115
単語: は, 重要度: 0.7739431858062744
単語: 。, 重要度: 0.40720391273498535
単語: い, 重要度: -1.893556833267212
単語: して, 重要度: -3.3165600299835205
単語: Python, 重要度: -6.764240264892578
単語: 私, 重要度: -17.49574851989746

Pythonの重要度が低いだとそれも関連性がない...そんなはずは。小文字にしてみよう!

$ python3 vector_words.py
テキストを入力して下さい。
私はpythonを勉強しています。
単語: ます, 重要度: 4.842738151550293
単語: 勉強, 重要度: 4.570006370544434
単語: を, 重要度: 3.3558690547943115
単語: は, 重要度: 0.7739431858062744
単語: 。, 重要度: 0.40720391273498535
単語: い, 重要度: -1.893556833267212
単語: して, 重要度: -3.3165600299835205
単語: python, 重要度: -6.764240264892578
単語: 私, 重要度: -17.49574851989746

ダメだ。

tokenized_text.insert(0, '[CLS]')
tokenized_text.append('[SEP]')

のような文の最初と最後が分かるように追加したら変わる訳ないよねぇ...

# jumanppを用いて分解
token_text = jumanpp.analysis(text)
tokenized_text = [mrph.midasi for mrph in token_text.mrph_list()]

# 文章の初めと最後を分かるように追加
tokenized_text.insert(0, '[CLS]')
tokenized_text.append('[SEP]')

# BERTで扱えるように変換
tokens = bert_tokenizer.convert_tokens_to_ids(tokenized_text)
tokens_tensor = torch.tensor([tokens])

この位置に追記。さてさて実行...

$ python3 vector_words.py
テキストを入力して下さい。
私はpythonを勉強しています。
単語: python, 重要度: 8.623164176940918
単語: い, 重要度: 6.1172661781311035
単語: 私, 重要度: 5.426082611083984
単語: を, 重要度: 3.8341915607452393
単語: ます, 重要度: 0.23174874484539032
単語: 勉強, 重要度: -2.1512906551361084
単語: 。, 重要度: -3.630830764770508
単語: [SEP], 重要度: -3.688336133956909
単語: して, 重要度: -4.338310718536377
単語: は, 重要度: -13.937437057495117
単語: [CLS], 重要度: -18.0908145904541

うん。pythonの重要度は上がった。勉強は下がった。「私pythonをいます」まぁまぁ日本人なら通じるか！
ってことで今回はここまでにします。

まとめ

ディレクトリの構造

japanese_model
            |_ vector_words.py
            |_ Japanese_L-24_H
                            |_ bert_config.json
                                    .
                                    .
                                    .

解凍したzipは名前が長すぎたので変えました。学習モデルが用意している語彙を読ませて今回は実行しています。