{"id":479358,"date":"2023-08-09T10:33:53","date_gmt":"2023-08-09T10:33:53","guid":{"rendered":""},"modified":"2023-09-05T11:18:39","modified_gmt":"2023-09-05T11:18:39","slug":"topic-modeling-algorithms-lda-nmf-plsa","status":"publish","type":"wiki","link":"https:\/\/oneproxy.pro\/tr\/wiki\/topic-modeling-algorithms-lda-nmf-plsa\/","title":{"rendered":"Konu modelleme algoritmalar\u0131 (LDA, NMF, PLSA)"},"content":{"rendered":"

Konu modelleme algoritmalar\u0131, do\u011fal dil i\u015fleme ve makine \u00f6\u011frenimi alan\u0131nda, b\u00fcy\u00fck metinsel veri koleksiyonlar\u0131 i\u00e7indeki gizli anlamsal yap\u0131lar\u0131 ke\u015ffetmek i\u00e7in tasarlanm\u0131\u015f g\u00fc\u00e7l\u00fc ara\u00e7lard\u0131r. Bu algoritmalar, bir belge toplulu\u011fundan gizli konular\u0131 \u00e7\u0131karmam\u0131za olanak tan\u0131yarak, \u00e7ok b\u00fcy\u00fck miktardaki metinsel bilginin daha iyi anla\u015f\u0131lmas\u0131n\u0131 ve organize edilmesini sa\u011flar. En yayg\u0131n kullan\u0131lan konu modelleme teknikleri aras\u0131nda Gizli Dirichlet Tahsisi (LDA), Negatif Olmayan Matris Faktorizasyon (NMF) ve Olas\u0131l\u0131ksal Gizli Semantik Analiz (PLSA) yer al\u0131r. Bu makalede bu konu modelleme algoritmalar\u0131n\u0131n tarihini, i\u00e7 yap\u0131s\u0131n\u0131, temel \u00f6zelliklerini, t\u00fcrlerini, uygulamalar\u0131n\u0131 ve gelece\u011fe y\u00f6nelik perspektiflerini inceleyece\u011fiz.<\/p>\n

Konu Modelleme Algoritmalar\u0131n\u0131n (LDA, NMF, PLSA) k\u00f6keninin tarihi ve ilk s\u00f6z\u00fc.<\/h2>\n

Konu modellemenin tarihi, ara\u015ft\u0131rmac\u0131lar\u0131n b\u00fcy\u00fck metinsel veri k\u00fcmelerinde altta yatan konular\u0131 ortaya \u00e7\u0131karmak i\u00e7in istatistiksel y\u00f6ntemleri ke\u015ffetmeye ba\u015flad\u0131klar\u0131 1990'lara kadar uzan\u0131yor. Konu modellemenin ilk s\u00f6zlerinden biri, Olas\u0131l\u0131ksal Gizli Anlamsal Analiz (PLSA) algoritmas\u0131n\u0131 2004'te "Bilimsel konular\u0131 bulma" ba\u015fl\u0131kl\u0131 makalelerinde tan\u0131tan Thomas L. Griffiths ve Mark Steyvers'a kadar uzanabilir. PLSA, belgelerdeki kelimelerin birlikte olu\u015fum kal\u0131plar\u0131n\u0131 ba\u015far\u0131l\u0131 bir \u015fekilde modelledi\u011fi ve gizli konular\u0131 belirledi\u011fi i\u00e7in o zamanlar devrim niteli\u011findeydi.<\/p>\n

PLSA'n\u0131n ard\u0131ndan ara\u015ft\u0131rmac\u0131lar David Blei, Andrew Y. Ng ve Michael I. Jordan, 2003 tarihli "Gizli Dirichlet Tahsisi" makalesinde Gizli Dirichlet Tahsisi (LDA) algoritmas\u0131n\u0131 sundular. LDA, PLSA'n\u0131n s\u0131n\u0131rlamalar\u0131n\u0131 ele almadan \u00f6nce Dirichlet kullanan \u00fcretken olas\u0131l\u0131ksal bir model sunarak PLSA'y\u0131 geni\u015fletti.<\/p>\n

Negatif Olmayan Matris Faktorizasyon (NMF), 1990'lardan beri var olan ve metin madencili\u011fi ve belge k\u00fcmeleme ba\u011flam\u0131nda pop\u00fclerlik kazanan ba\u015fka bir konu modelleme tekni\u011fidir.<\/p>\n

Konu Modelleme Algoritmalar\u0131 (LDA, NMF, PLSA) hakk\u0131nda detayl\u0131 bilgi<\/h2>\n

Konu Modelleme Algoritmalar\u0131n\u0131n (LDA, NMF, PLSA) i\u00e7 yap\u0131s\u0131<\/h3>\n
    \n
  1. \n

    Gizli Dirichlet Tahsisi (LDA):
    \nLDA, belgelerin gizli konular\u0131n kar\u0131\u015f\u0131m\u0131 oldu\u011funu ve konular\u0131n kelimeler \u00fczerindeki da\u011f\u0131l\u0131mlar oldu\u011funu varsayan \u00fcretken bir olas\u0131l\u0131ksal modeldir. LDA'n\u0131n i\u00e7 yap\u0131s\u0131 iki rastgele de\u011fi\u015fken katman\u0131n\u0131 i\u00e7erir: belge-konu da\u011f\u0131l\u0131m\u0131 ve konu-kelime da\u011f\u0131l\u0131m\u0131. Algoritma, yak\u0131nsamaya kadar yinelemeli olarak s\u00f6zc\u00fckleri konulara, belgeleri de konu kar\u0131\u015f\u0131mlar\u0131na atar ve temel konular\u0131 ve bunlar\u0131n s\u00f6zc\u00fck da\u011f\u0131l\u0131mlar\u0131n\u0131 ortaya \u00e7\u0131kar\u0131r.<\/p>\n<\/li>\n

  2. \n

    Negatif Olmayan Matris Faktorizasyon (NMF):
    \nNMF, terim-belge matrisini negatif olmayan iki matrise ay\u0131ran do\u011frusal cebir tabanl\u0131 bir y\u00f6ntemdir: biri konular\u0131, di\u011feri ise konu-belge da\u011f\u0131l\u0131m\u0131n\u0131 temsil eder. NMF, yorumlanabilirli\u011fi sa\u011flamak i\u00e7in olumsuz olmamay\u0131 zorunlu k\u0131lar ve konu modellemeye ek olarak genellikle boyut azaltma ve k\u00fcmeleme i\u00e7in kullan\u0131l\u0131r.<\/p>\n<\/li>\n

  3. \n

    Olas\u0131l\u0131ksal Gizli Anlamsal Analiz (PLSA):
    \nPLSA, LDA gibi, belgeleri gizli konular\u0131n kar\u0131\u015f\u0131m\u0131 olarak temsil eden olas\u0131l\u0131ksal bir modeldir. Belgenin konusuna g\u00f6re bir belgede ge\u00e7en bir kelimenin olas\u0131l\u0131\u011f\u0131n\u0131 do\u011frudan modeller. Ancak PLSA, LDA'da mevcut olan Bayes \u00e7\u0131kar\u0131m \u00e7er\u00e7evesinden yoksundur.<\/p>\n<\/li>\n<\/ol>\n

    Konu Modelleme Algoritmalar\u0131n\u0131n (LDA, NMF, PLSA) temel \u00f6zelliklerinin analizi<\/h2>\n

    Konu Modelleme Algoritmalar\u0131n\u0131n (LDA, NMF, PLSA) temel \u00f6zellikleri \u015funlar\u0131 i\u00e7erir:<\/p>\n

      \n
    1. \n

      Konu Yorumlanabilirli\u011fi<\/strong>: Her \u00fc\u00e7 algoritma da insanlar taraf\u0131ndan yorumlanabilen konular olu\u015fturarak, b\u00fcy\u00fck metinsel veri k\u00fcmelerinde mevcut olan temel temalar\u0131n anla\u015f\u0131lmas\u0131n\u0131 ve analiz edilmesini kolayla\u015ft\u0131r\u0131r.<\/p>\n<\/li>\n

    2. \n

      Denetimsiz \u00d6\u011frenme<\/strong>: Konu modelleme denetimsiz bir \u00f6\u011frenme tekni\u011fidir, yani e\u011fitim i\u00e7in etiketli verilere ihtiya\u00e7 duymaz. Bu, onu \u00e7ok y\u00f6nl\u00fc ve \u00e7e\u015fitli alanlara uygulanabilir hale getirir.<\/p>\n<\/li>\n

    3. \n

      \u00d6l\u00e7eklenebilirlik<\/strong>: Her algoritman\u0131n verimlili\u011fi farkl\u0131l\u0131k g\u00f6sterse de bilgi i\u015flem kaynaklar\u0131ndaki geli\u015fmeler, konu modellemeyi b\u00fcy\u00fck veri k\u00fcmelerini i\u015fleyecek \u015fekilde \u00f6l\u00e7eklenebilir hale getirdi.<\/p>\n<\/li>\n

    4. \n

      Geni\u015f Uygulanabilirlik<\/strong>: Konu modelleme, bilgi eri\u015fimi, duygu analizi, i\u00e7erik \u00f6nerisi ve sosyal a\u011f analizi gibi \u00e7e\u015fitli alanlarda uygulama alan\u0131 bulmu\u015ftur.<\/p>\n<\/li>\n<\/ol>\n

      Konu Modelleme Algoritma T\u00fcrleri (LDA, NMF, PLSA)<\/h2>\n\n\n\n\n\n\n\n\n\n\n\n\n
      Algoritma<\/th>\nTemel \u00f6zellikler<\/th>\n<\/tr>\n<\/thead>\n
      Gizli Dirichlet Tahsisi<\/td>\n\u2013 \u00dcretken model<\/td>\n<\/tr>\n
      <\/td>\n\u2013 Bayes \u00e7\u0131kar\u0131m\u0131<\/td>\n<\/tr>\n
      <\/td>\n\u2013 Belge-konu ve konu-kelime da\u011f\u0131l\u0131mlar\u0131<\/td>\n<\/tr>\n
      Negatif Olmayan Matris Faktorizasyon<\/td>\n\u2013 Do\u011frusal cebire dayal\u0131 y\u00f6ntem<\/td>\n<\/tr>\n
      <\/td>\n\u2013 Negatif olmama k\u0131s\u0131tlamas\u0131<\/td>\n<\/tr>\n
      Olas\u0131l\u0131ksal Gizli Anlamsal Analiz<\/td>\n\u2013 Olas\u0131l\u0131ksal model<\/td>\n<\/tr>\n
      <\/td>\n\u2013 Bayes \u00e7\u0131kar\u0131m\u0131 yok<\/td>\n<\/tr>\n
      <\/td>\n\u2013 Konulara g\u00f6re verilen kelime olas\u0131l\u0131klar\u0131n\u0131 do\u011frudan modeller<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

      Konu Modelleme Algoritmalar\u0131n\u0131n (LDA, NMF, PLSA) kullan\u0131m yollar\u0131, kullan\u0131mla ilgili sorunlar ve \u00e7\u00f6z\u00fcmleri.<\/h2>\n

      Konu modelleme algoritmalar\u0131 \u00e7e\u015fitli alanlarda uygulamalar bulur:<\/p>\n

        \n
      1. \n

        Bilgi alma<\/strong>: Konu modelleme, b\u00fcy\u00fck metin derlemlerinden bilgilerin verimli bir \u015fekilde d\u00fczenlenmesine ve al\u0131nmas\u0131na yard\u0131mc\u0131 olur.<\/p>\n<\/li>\n

      2. \n

        Duygu Analizi<\/strong>: \u0130\u015fletmeler, m\u00fc\u015fteri incelemeleri ve geri bildirimlerindeki konular\u0131 belirleyerek duyarl\u0131l\u0131k e\u011filimlerine ili\u015fkin \u00f6ng\u00f6r\u00fcler elde edebilir.<\/p>\n<\/li>\n

      3. \n

        \u0130\u00e7erik \u00d6nerisi<\/strong>: \u00d6neri sistemleri, kullan\u0131c\u0131lara ilgi alanlar\u0131na g\u00f6re alakal\u0131 i\u00e7erik \u00f6nermek i\u00e7in konu modellemeyi kullan\u0131r.<\/p>\n<\/li>\n

      4. \n

        Sosyal A\u011f Analizi<\/strong>: Konu modelleme, sosyal a\u011flardaki tart\u0131\u015fmalar\u0131n ve topluluklar\u0131n dinamiklerini anlamaya yard\u0131mc\u0131 olur.<\/p>\n<\/li>\n<\/ol>\n

        Ancak konu modelleme algoritmalar\u0131n\u0131n kullan\u0131lmas\u0131 a\u015fa\u011f\u0131daki gibi zorluklar do\u011furabilir:<\/p>\n

          \n
        1. \n

          Hesaplamal\u0131 Karma\u015f\u0131kl\u0131k<\/strong>: Konu modelleme, \u00f6zellikle b\u00fcy\u00fck veri k\u00fcmelerinde hesaplama a\u00e7\u0131s\u0131ndan yo\u011fun olabilir. \u00c7\u00f6z\u00fcmler aras\u0131nda da\u011f\u0131t\u0131lm\u0131\u015f hesaplama veya yakla\u015f\u0131k \u00e7\u0131kar\u0131m y\u00f6ntemlerinin kullan\u0131lmas\u0131 yer al\u0131r.<\/p>\n<\/li>\n

        2. \n

          Konu Say\u0131s\u0131n\u0131n Belirlenmesi<\/strong>: En uygun konu say\u0131s\u0131n\u0131n se\u00e7ilmesi a\u00e7\u0131k bir ara\u015ft\u0131rma problemi olmaya devam etmektedir. \u015ea\u015fk\u0131nl\u0131k ve tutarl\u0131l\u0131k \u00f6l\u00e7\u00fcmleri gibi teknikler, en uygun konu say\u0131s\u0131n\u0131n belirlenmesine yard\u0131mc\u0131 olabilir.<\/p>\n<\/li>\n

        3. \n

          Belirsiz Konular\u0131 Yorumlamak<\/strong>: Baz\u0131 konular iyi tan\u0131mlanmam\u0131\u015f olabilir, bu da yorumlanmas\u0131n\u0131 zorla\u015ft\u0131r\u0131r. Konu etiketleme gibi i\u015flem sonras\u0131 teknikler yorumlanabilirli\u011fi geli\u015ftirebilir.<\/p>\n<\/li>\n<\/ol>\n

          Ana \u00f6zellikler ve benzer terimlerle di\u011fer kar\u015f\u0131la\u015ft\u0131rmalar tablo ve liste \u015feklinde.<\/h2>\n\n\n\n\n\n\n\n\n\n
          karakteristik<\/th>\nGizli Dirichlet Tahsisi<\/th>\nNegatif Olmayan Matris Faktorizasyon<\/th>\nOlas\u0131l\u0131ksal Gizli Anlamsal Analiz<\/th>\n<\/tr>\n<\/thead>\n
          \u00dcretken Model<\/td>\nEvet<\/td>\nHAYIR<\/td>\nEvet<\/td>\n<\/tr>\n
          Bayes \u00c7\u0131kar\u0131m\u0131<\/td>\nEvet<\/td>\nHAYIR<\/td>\nHAYIR<\/td>\n<\/tr>\n
          Olumsuzluk K\u0131s\u0131tlamas\u0131<\/td>\nHAYIR<\/td>\nEvet<\/td>\nHAYIR<\/td>\n<\/tr>\n
          Yorumlanabilir Konular<\/td>\nEvet<\/td>\nEvet<\/td>\nEvet<\/td>\n<\/tr>\n
          \u00d6l\u00e7eklenebilir<\/td>\nEvet<\/td>\nEvet<\/td>\nEvet<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

          Konu Modelleme Algoritmalar\u0131na (LDA, NMF, PLSA) ili\u015fkin gelece\u011fin perspektifleri ve teknolojileri.<\/h2>\n

          Teknoloji ilerlemeye devam ettik\u00e7e konu modelleme algoritmalar\u0131n\u0131n \u015funlardan faydalanmas\u0131 muhtemeldir:<\/p>\n

            \n
          1. \n

            Geli\u015ftirilmi\u015f \u00d6l\u00e7eklenebilirlik<\/strong>: Da\u011f\u0131t\u0131lm\u0131\u015f bilgi i\u015flem ve paralel i\u015flemenin b\u00fcy\u00fcmesiyle, konu modelleme algoritmalar\u0131 daha b\u00fcy\u00fck ve daha \u00e7e\u015fitli veri k\u00fcmelerini i\u015flemede daha verimli hale gelecektir.<\/p>\n<\/li>\n

          2. \n

            Derin \u00d6\u011frenme ile Entegrasyon<\/strong>: Konu modellemeyi derin \u00f6\u011frenme teknikleriyle entegre etmek, geli\u015fmi\u015f konu temsillerine ve sonraki g\u00f6revlerde daha iyi performansa yol a\u00e7abilir.<\/p>\n<\/li>\n

          3. \n

            Ger\u00e7ek Zamanl\u0131 Konu Analizi<\/strong>: Ger\u00e7ek zamanl\u0131 veri i\u015flemedeki geli\u015fmeler, uygulamalar\u0131n ak\u0131\u015fl\u0131 metin verileri \u00fczerinde konu modellemesi ger\u00e7ekle\u015ftirmesine olanak tan\u0131yacak ve sosyal medya izleme ve haber analizi gibi alanlarda yeni olas\u0131l\u0131klar\u0131n \u00f6n\u00fcn\u00fc a\u00e7acak.<\/p>\n<\/li>\n<\/ol>\n

            Proxy sunucular\u0131 nas\u0131l kullan\u0131labilir veya Konu Modelleme Algoritmalar\u0131 (LDA, NMF, PLSA) ile nas\u0131l ili\u015fkilendirilebilir?<\/h2>\n

            OneProxy gibi \u015firketlerin sa\u011flad\u0131\u011f\u0131 proxy sunucular, konu modelleme algoritmalar\u0131n\u0131n kullan\u0131m\u0131n\u0131 kolayla\u015ft\u0131rmada \u00f6nemli bir rol oynayabilir. Proxy sunucular\u0131, kullan\u0131c\u0131lar ile internet aras\u0131nda arac\u0131 g\u00f6revi g\u00f6rerek, kullan\u0131c\u0131lar\u0131n \u00e7evrimi\u00e7i kaynaklara daha g\u00fcvenli ve \u00f6zel bir \u015fekilde eri\u015fmelerine olanak tan\u0131r. Konu modelleme ba\u011flam\u0131nda proxy sunucular \u015fu konularda yard\u0131mc\u0131 olabilir:<\/p>\n

              \n
            1. \n

              Veri toplama<\/strong>: Proxy sunucular\u0131, kullan\u0131c\u0131n\u0131n kimli\u011fini a\u00e7\u0131klamadan \u00e7e\u015fitli \u00e7evrimi\u00e7i kaynaklardan web kaz\u0131ma ve veri toplama olana\u011f\u0131 sa\u011flar, anonimli\u011fi sa\u011flar ve IP tabanl\u0131 k\u0131s\u0131tlamalar\u0131 \u00f6nler.<\/p>\n<\/li>\n

            2. \n

              \u00d6l\u00e7eklenebilirlik<\/strong>: B\u00fcy\u00fck \u00f6l\u00e7ekli konu modelleme, ayn\u0131 anda birden fazla \u00e7evrimi\u00e7i kayna\u011fa eri\u015fmeyi gerektirebilir. Proxy sunucular\u0131 y\u00fcksek hacimli istekleri i\u015fleyebilir, y\u00fck\u00fc da\u011f\u0131tabilir ve \u00f6l\u00e7eklenebilirli\u011fi geli\u015ftirebilir.<\/p>\n<\/li>\n

            3. \n

              Co\u011frafi \u00c7e\u015fitlilik<\/strong>: Yerelle\u015ftirilmi\u015f i\u00e7erik veya \u00e7ok dilli veri k\u00fcmeleri \u00fczerinde konu modelleme, farkl\u0131 IP konumlar\u0131na sahip farkl\u0131 proxy'lere eri\u015fimden yararlanarak daha kapsaml\u0131 bir analiz sunar.<\/p>\n<\/li>\n<\/ol>\n

              \u0130lgili Ba\u011flant\u0131lar<\/h2>\n

              Konu Modelleme Algoritmalar\u0131 (LDA, NMF, PLSA) hakk\u0131nda daha fazla bilgi i\u00e7in a\u015fa\u011f\u0131daki kaynaklara ba\u015fvurabilirsiniz:<\/p>\n

                \n
              1. Olas\u0131l\u0131ksal Gizli Semantik Analiz (PLSA) \u2013 Orijinal Makale<\/a><\/li>\n
              2. Gizli Dirichlet Tahsisi (LDA) \u2013 Orijinal Makale<\/a><\/li>\n
              3. Negatif Olmayan Matris Faktorizasyon (NMF) \u2013 Orijinal Ka\u011f\u0131t<\/a><\/li>\n<\/ol>","protected":false},"featured_media":0,"menu_order":0,"template":"","meta":{"_acf_changed":false,"content-type":"","inline_featured_image":false,"footnotes":""},"class_list":["post-479358","wiki","type-wiki","status-publish","hentry"],"acf":{"faq_title":"Frequently Asked Questions about Topic Modeling Algorithms (LDA, NMF, PLSA)<\/mark>","faq_items":[{"question":"What are topic modeling algorithms, and why are they important?","answer":"

                Topic modeling algorithms, such as LDA, NMF, and PLSA, are powerful tools in natural language processing that uncover hidden themes or topics within large collections of text data. They are crucial for understanding and organizing vast amounts of textual information, making it easier to extract meaningful insights and patterns.<\/p>"},{"question":"What is the history behind topic modeling algorithms?","answer":"

                Topic modeling has its roots in the 1990s when researchers started exploring statistical methods to uncover latent topics in textual data. The first mention of topic modeling can be traced back to the introduction of Probabilistic Latent Semantic Analysis (PLSA) in 2004 by Thomas L. Griffiths and Mark Steyvers. Later, in 2003, Latent Dirichlet Allocation (LDA) was proposed by David Blei, Andrew Y. Ng, and Michael I. Jordan, expanding upon PLSA with a Bayesian framework. Non-Negative Matrix Factorization (NMF) also emerged as a popular technique for topic modeling.<\/p>"},{"question":"How do topic modeling algorithms work?","answer":"

                Topic modeling algorithms work by analyzing the co-occurrence patterns of words in documents to identify latent topics. LDA and PLSA use probabilistic models to represent documents as mixtures of topics, while NMF employs linear algebra to factorize the term-document matrix into non-negative matrices representing topics and their distribution across documents.<\/p>"},{"question":"What are the key features of topic modeling algorithms?","answer":"

                The key features of topic modeling algorithms include their ability to generate interpretable topics, unsupervised learning capability (no labeled data required), scalability to handle large datasets, and wide applicability in various fields such as information retrieval, sentiment analysis, content recommendation, and social network analysis.<\/p>"},{"question":"What types of topic modeling algorithms exist, and how do they differ?","answer":"

                There are three main types of topic modeling algorithms: LDA, NMF, and PLSA. LDA and PLSA are generative probabilistic models that use Bayesian inference, while NMF is a linear algebra-based method with a non-negativity constraint to ensure interpretability.<\/p>"},{"question":"How can topic modeling algorithms be used, and what are the challenges?","answer":"

                Topic modeling algorithms find applications in information retrieval, sentiment analysis, content recommendation, and social network analysis. However, challenges may include computational complexity, determining the optimal number of topics, and interpreting ambiguous topics. Solutions include distributed computing, approximate inference methods, and post-processing techniques for topic labeling.<\/p>"},{"question":"What are the future perspectives of topic modeling algorithms?","answer":"

                The future of topic modeling is likely to see improved scalability, integration with deep learning techniques for better topic representations, and real-time analysis of streaming text data. Advancements in technology will further enhance the capabilities and applications of topic modeling algorithms.<\/p>"},{"question":"How are proxy servers associated with topic modeling algorithms?","answer":"

                Proxy servers, such as those provided by OneProxy, play a significant role in facilitating the usage of topic modeling algorithms. They enable secure and private data collection, enhance scalability for large-scale topic modeling, and provide geographical diversity for analyzing localized content and multilingual datasets.<\/p>"}]},"_links":{"self":[{"href":"https:\/\/oneproxy.pro\/tr\/wp-json\/wp\/v2\/wiki\/479358","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/oneproxy.pro\/tr\/wp-json\/wp\/v2\/wiki"}],"about":[{"href":"https:\/\/oneproxy.pro\/tr\/wp-json\/wp\/v2\/types\/wiki"}],"version-history":[{"count":0,"href":"https:\/\/oneproxy.pro\/tr\/wp-json\/wp\/v2\/wiki\/479358\/revisions"}],"wp:attachment":[{"href":"https:\/\/oneproxy.pro\/tr\/wp-json\/wp\/v2\/media?parent=479358"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}