ABOUT
Compressed ideographs -visualized- is a work that explores new ways of creating symbols through technology in order for ideographs to have a writing system that can adapt to the diversification of words and meanings.
In recent years, values have become increasingly complex and diverse. For example, previously discrete concepts such as gender and race (superficial diversity), work and language (deep diversity) have become continuous. However, they (concepts that exist between dots) can only be described by finite combinations of existing Chinese characters, and there is no unique symbol that can accurately represent them.
In this work, ideographs are generated by deep learning. The AI model DALL_E, which generates images from text, learns pairs of Chinese characters and sentences describing their meanings, and compresses any sentence input by the audience into a single Chinese character. Visualization is then performed by placing the existing Chinese characters in a space that corresponds to their meanings and locations, and displaying information about the generated ideographs.
Through this work, we attempt to contemplate the nature of letters and symbols by generating ideographs specific to each concept input by the audience, rather than using conventional combinations of existing characters.
In recent years, values have become increasingly complex and diverse. For example, previously discrete concepts such as gender and race (superficial diversity), work and language (deep diversity) have become continuous. However, they (concepts that exist between dots) can only be described by finite combinations of existing Chinese characters, and there is no unique symbol that can accurately represent them.
In this work, ideographs are generated by deep learning. The AI model DALL_E, which generates images from text, learns pairs of Chinese characters and sentences describing their meanings, and compresses any sentence input by the audience into a single Chinese character. Visualization is then performed by placing the existing Chinese characters in a space that corresponds to their meanings and locations, and displaying information about the generated ideographs.
Through this work, we attempt to contemplate the nature of letters and symbols by generating ideographs specific to each concept input by the audience, rather than using conventional combinations of existing characters.
Compressed ideographs -visualized-は，表意文字(1字1字が一定の意味を表す文字, ideographs)が語と意味の多様化に順応した文字体系を持つために，テクノロジーによって新たな記号の作り方を模索する作品である．
昨今では，価値観の複雑化・多様化が進んでいる．例えば性別や人種（表層的多様性），仕事や言語（深層的多様性）のように，以前は離散的であった概念が連続化している．しかし，それら（点と点の間に存在する概念）は既存の漢字による有限個の組み合わせのみで説明され，正確に表象できる固有の記号が存在しない．
本作品では，深層学習による表意文字の生成を行なう．テキストから画像を生成するAIモデルDALL_Eに漢字とその漢字の意味が説明された文章のペアを学習させ，鑑賞者が入力した任意の文章を１文字の漢字として圧縮する．そして，既存の漢字の意味と位置が対応した空間への配置や，生成された表意文字に関する情報の表示などのビジュアライゼーションが行われる．
本作品を通して，これまでの既存の文字の組み合わせによる表現ではなく，鑑賞者が入力するそれぞれの概念に特有の表意文字を生成することで，文字・記号のあり方の思索を試みる．
昨今では，価値観の複雑化・多様化が進んでいる．例えば性別や人種（表層的多様性），仕事や言語（深層的多様性）のように，以前は離散的であった概念が連続化している．しかし，それら（点と点の間に存在する概念）は既存の漢字による有限個の組み合わせのみで説明され，正確に表象できる固有の記号が存在しない．
本作品では，深層学習による表意文字の生成を行なう．テキストから画像を生成するAIモデルDALL_Eに漢字とその漢字の意味が説明された文章のペアを学習させ，鑑賞者が入力した任意の文章を１文字の漢字として圧縮する．そして，既存の漢字の意味と位置が対応した空間への配置や，生成された表意文字に関する情報の表示などのビジュアライゼーションが行われる．
本作品を通して，これまでの既存の文字の組み合わせによる表現ではなく，鑑賞者が入力するそれぞれの概念に特有の表意文字を生成することで，文字・記号のあり方の思索を試みる．
WORK
In this work, I was responsible for the implementation of deep learning to generate Kanji images from input sentences. Please see INFORMATION for technical details. I also produced the videos for version1 and version2.
本作品では、入力文から漢字画像を生成する深層学習の実装を担当しました。技術的な詳細についてはINFORMATIONをご確認ください。また、version1, version2の動画制作を行いました。
INFORMATION
https://medium.com/computational-creativity-lab-at-keio-sfc/cclab-21%E7%A7%8B-2021%E5%B9%B4%E5%BA%A6%E7%A7%8B%E5%AD%A6%E6%9C%9F-%E7%9F%B3%E4%BA%95%E9%A3%9B%E9%B3%A5%E3%81%AE%E6%B4%BB%E5%8B%95%E5%A0%B1%E5%91%8A-1062d1f72977
AWARD / EXHIBITION / CONFERENCE
・[Exibition] 慶應義塾大学SFC 徳井直生研究室 CCLab Exhibition 2021 Alternative Dimension (2021.9.23-2021.9.27 at Tiers Gallery, Tokyo, Japan)
・[Exhibition] TUB第12回企画展「Visible x Invisible ──ビッグデータと次世代の情報表現」 (2022.1.28-2022.2.12 at Tama Art University Bureau, Tokyo, Japan)
・[Award / Exhibition] Yamanashi Media Arts Award 2021 Y-SILVER(優秀賞) (2022.2.3-2022.2.6 at Yamanashi Prefectural Museum of Art, Yamanashi, Japan)
・[Award / Exhibition] Asia Digital Art Award 2021 General Category Interactive Arts Finalists' Award (2022.3.8-2022.3.13 at Fukuoka Art Museum, Fukuoka, Japan)
・[Exhibition] MUSES EX MACHINA - AIが映し出す人と創造性の未来 at ICC アニュアル 2022 生命的なものたち (2022.6.25-2022.9.11 at NTTインターコミュニケーション・センター [ICC] )
VIDEO (2nd edition)
VIDEO (1st edition)
PHOTOGRAPH
Exhibition at TIERS GALLERY, Sep. 2021
Exhibition at TIERS GALLERY, Sep. 2021
Exhibition at Tama Art University Bureau, Jan. 2022
Exhibition at Yamanashi Prefectural Museum of Art, Feb. 2022
Exhibition at Tama Art University Bureau, Jan. 2022
Exhibition at Fukuoka Art Museum, Mar. 2022
Exhibition at Fukuoka Art Museum, Mar. 2022
Exhibition at Yamanashi Prefectural Museum of Art, Feb. 2022
Exhibition at Yamanashi Prefectural Museum of Art, Feb. 2022
Exhibition at Yamanashi Prefectural Museum of Art, Feb. 2022
Exhibition at Yamanashi Prefectural Museum of Art, Feb. 2022
Exhibition at Intercommunication Center, Sep. 2022
Exhibition at Intercommunication Center, Sep. 2022
Exhibition at Intercommunication Center, Sep. 2022
CREDIT
Direction, Machine learning, Visual programming: Scott Allen
Machine learning, Visual programming: Keito Takaishi
Machine learning, Video: Asuka Ishii
Machine learning, Visual programming: Kazufumi Shibuya
Visual programming: Yuma Matsuoka
Sound: Atsuya Kobayashi
Support(ver1, 2): Muhan Li
Technical advice: Nao Tokui
Thanks: Keio University SFC Computational Creativity Lab (Nao Tokui Lab)
Machine learning, Visual programming: Keito Takaishi
Machine learning, Video: Asuka Ishii
Machine learning, Visual programming: Kazufumi Shibuya
Visual programming: Yuma Matsuoka
Sound: Atsuya Kobayashi
Support(ver1, 2): Muhan Li
Technical advice: Nao Tokui
Thanks: Keio University SFC Computational Creativity Lab (Nao Tokui Lab)
Thanks(video - 1st edition):
Soshi Yamaguchi (Sound equipment cooperation)
Momokan (Cast)
TIERS GALLERY
Soshi Yamaguchi (Sound equipment cooperation)
Momokan (Cast)
TIERS GALLERY
Thanks(video - 2nd edition):
Haruka Komano (Cast)
Tama Art University Bureau
Haruka Komano (Cast)
Tama Art University Bureau