{"id":478929,"date":"2023-08-09T09:40:29","date_gmt":"2023-08-09T09:40:29","guid":{"rendered":""},"modified":"2023-09-05T11:17:49","modified_gmt":"2023-09-05T11:17:49","slug":"sequence-to-sequence-models-seq2seq","status":"publish","type":"wiki","link":"https:\/\/oneproxy.pro\/vn\/wiki\/sequence-to-sequence-models-seq2seq\/","title":{"rendered":"C\u00e1c m\u00f4 h\u00ecnh theo tr\u00ecnh t\u1ef1 (Seq2Seq)"},"content":{"rendered":"<p>M\u00f4 h\u00ecnh Sequence-to-Sequence (Seq2Seq) l\u00e0 m\u1ed9t l\u1edbp m\u00f4 h\u00ecnh h\u1ecdc s\u00e2u \u0111\u01b0\u1ee3c thi\u1ebft k\u1ebf \u0111\u1ec3 d\u1ecbch c\u00e1c chu\u1ed7i t\u1eeb m\u1ed9t mi\u1ec1n (v\u00ed d\u1ee5: c\u00e1c c\u00e2u b\u1eb1ng ti\u1ebfng Anh) th\u00e0nh c\u00e1c chu\u1ed7i trong m\u1ed9t mi\u1ec1n kh\u00e1c (v\u00ed d\u1ee5: c\u00e1c b\u1ea3n d\u1ecbch t\u01b0\u01a1ng \u1ee9ng b\u1eb1ng ti\u1ebfng Ph\u00e1p). Ch\u00fang c\u00f3 \u1ee9ng d\u1ee5ng trong nhi\u1ec1u l\u0129nh v\u1ef1c kh\u00e1c nhau, bao g\u1ed3m x\u1eed l\u00fd ng\u00f4n ng\u1eef t\u1ef1 nhi\u00ean, nh\u1eadn d\u1ea1ng gi\u1ecdng n\u00f3i v\u00e0 d\u1ef1 b\u00e1o chu\u1ed7i th\u1eddi gian.<\/p>\n<h2>L\u1ecbch s\u1eed ngu\u1ed3n g\u1ed1c c\u1ee7a c\u00e1c m\u00f4 h\u00ecnh tu\u1ea7n t\u1ef1 (Seq2Seq) v\u00e0 s\u1ef1 \u0111\u1ec1 c\u1eadp \u0111\u1ea7u ti\u00ean v\u1ec1 n\u00f3<\/h2>\n<p>C\u00e1c m\u00f4 h\u00ecnh Seq2Seq \u0111\u01b0\u1ee3c c\u00e1c nh\u00e0 nghi\u00ean c\u1ee9u c\u1ee7a Google gi\u1edbi thi\u1ec7u l\u1ea7n \u0111\u1ea7u ti\u00ean v\u00e0o n\u0103m 2014. B\u00e0i b\u00e1o c\u00f3 ti\u00eau \u0111\u1ec1 \u201cH\u1ecdc t\u1eeb tr\u00ecnh t\u1ef1 \u0111\u1ebfn tr\u00ecnh t\u1ef1 v\u1edbi M\u1ea1ng th\u1ea7n kinh\u201d \u0111\u00e3 m\u00f4 t\u1ea3 m\u00f4 h\u00ecnh ban \u0111\u1ea7u, bao g\u1ed3m hai M\u1ea1ng th\u1ea7n kinh t\u00e1i ph\u00e1t (RNN): m\u1ed9t b\u1ed9 m\u00e3 h\u00f3a \u0111\u1ec3 x\u1eed l\u00fd chu\u1ed7i \u0111\u1ea7u v\u00e0o v\u00e0 m\u1ed9t b\u1ed9 gi\u1ea3i m\u00e3 \u0111\u1ec3 t\u1ea1o ra chu\u1ed7i \u0111\u1ea7u ra t\u01b0\u01a1ng \u1ee9ng. Kh\u00e1i ni\u1ec7m n\u00e0y nhanh ch\u00f3ng thu h\u00fat \u0111\u01b0\u1ee3c s\u1ef1 ch\u00fa \u00fd v\u00e0 truy\u1ec1n c\u1ea3m h\u1ee9ng cho nghi\u00ean c\u1ee9u v\u00e0 ph\u00e1t tri\u1ec3n s\u00e2u h\u01a1n.<\/p>\n<h2>Th\u00f4ng tin chi ti\u1ebft v\u1ec1 c\u00e1c m\u00f4 h\u00ecnh tu\u1ea7n t\u1ef1 (Seq2Seq): M\u1edf r\u1ed9ng ch\u1ee7 \u0111\u1ec1<\/h2>\n<p>C\u00e1c m\u00f4 h\u00ecnh Seq2Seq \u0111\u01b0\u1ee3c thi\u1ebft k\u1ebf \u0111\u1ec3 x\u1eed l\u00fd c\u00e1c t\u00e1c v\u1ee5 d\u1ef1a tr\u00ean tr\u00ecnh t\u1ef1 kh\u00e1c nhau. M\u00f4 h\u00ecnh bao g\u1ed3m:<\/p>\n<ol>\n<li>\n<p><strong>M\u00e3 ho\u00e1<\/strong>: Ph\u1ea7n n\u00e0y c\u1ee7a m\u00f4 h\u00ecnh nh\u1eadn chu\u1ed7i \u0111\u1ea7u v\u00e0o v\u00e0 n\u00e9n th\u00f4ng tin v\u00e0o vect\u01a1 ng\u1eef c\u1ea3nh c\u00f3 \u0111\u1ed9 d\u00e0i c\u1ed1 \u0111\u1ecbnh. Th\u00f4ng th\u01b0\u1eddng, n\u00f3 li\u00ean quan \u0111\u1ebfn vi\u1ec7c s\u1eed d\u1ee5ng RNN ho\u1eb7c c\u00e1c bi\u1ebfn th\u1ec3 c\u1ee7a n\u00f3 nh\u01b0 m\u1ea1ng B\u1ed9 nh\u1edb ng\u1eafn h\u1ea1n d\u00e0i (LSTM).<\/p>\n<\/li>\n<li>\n<p><strong>B\u1ed9 gi\u1ea3i m\u00e3<\/strong>: N\u00f3 l\u1ea5y vect\u01a1 ng\u1eef c\u1ea3nh do b\u1ed9 m\u00e3 h\u00f3a t\u1ea1o ra v\u00e0 t\u1ea1o ra m\u1ed9t chu\u1ed7i \u0111\u1ea7u ra. N\u00f3 c\u0169ng \u0111\u01b0\u1ee3c x\u00e2y d\u1ef1ng b\u1eb1ng RNN ho\u1eb7c LSTM v\u00e0 \u0111\u01b0\u1ee3c \u0111\u00e0o t\u1ea1o \u0111\u1ec3 d\u1ef1 \u0111o\u00e1n m\u1ee5c ti\u1ebfp theo trong chu\u1ed7i d\u1ef1a tr\u00ean c\u00e1c m\u1ee5c tr\u01b0\u1edbc \u0111\u00f3.<\/p>\n<\/li>\n<li>\n<p><strong>\u0110\u00e0o t\u1ea1o<\/strong>: C\u1ea3 b\u1ed9 m\u00e3 h\u00f3a v\u00e0 b\u1ed9 gi\u1ea3i m\u00e3 \u0111\u1ec1u \u0111\u01b0\u1ee3c hu\u1ea5n luy\u1ec7n c\u00f9ng nhau b\u1eb1ng c\u00e1ch s\u1eed d\u1ee5ng lan truy\u1ec1n ng\u01b0\u1ee3c, th\u01b0\u1eddng l\u00e0 b\u1eb1ng thu\u1eadt to\u00e1n t\u1ed1i \u01b0u h\u00f3a d\u1ef1a tr\u00ean \u0111\u1ed9 d\u1ed1c.<\/p>\n<\/li>\n<\/ol>\n<h2>C\u1ea5u tr\u00fac b\u00ean trong c\u1ee7a c\u00e1c m\u00f4 h\u00ecnh tu\u1ea7n t\u1ef1 (Seq2Seq): C\u00e1ch th\u1ee9c ho\u1ea1t \u0111\u1ed9ng<\/h2>\n<p>C\u1ea5u tr\u00fac \u0111i\u1ec3n h\u00ecnh c\u1ee7a m\u00f4 h\u00ecnh Seq2Seq bao g\u1ed3m:<\/p>\n<ol>\n<li><strong>X\u1eed l\u00fd \u0111\u1ea7u v\u00e0o<\/strong>: Tr\u00ecnh t\u1ef1 \u0111\u1ea7u v\u00e0o \u0111\u01b0\u1ee3c b\u1ed9 m\u00e3 h\u00f3a x\u1eed l\u00fd theo t\u1eebng b\u01b0\u1edbc th\u1eddi gian, thu th\u1eadp th\u00f4ng tin c\u1ea7n thi\u1ebft trong vect\u01a1 ng\u1eef c\u1ea3nh.<\/li>\n<li><strong>T\u1ea1o vect\u01a1 b\u1ed1i c\u1ea3nh<\/strong>: Tr\u1ea1ng th\u00e1i cu\u1ed1i c\u00f9ng c\u1ee7a RNN c\u1ee7a b\u1ed9 m\u00e3 h\u00f3a bi\u1ec3u th\u1ecb b\u1ed1i c\u1ea3nh c\u1ee7a to\u00e0n b\u1ed9 chu\u1ed7i \u0111\u1ea7u v\u00e0o.<\/li>\n<li><strong>T\u1ea1o \u0111\u1ea7u ra<\/strong>: B\u1ed9 gi\u1ea3i m\u00e3 l\u1ea5y vect\u01a1 ng\u1eef c\u1ea3nh v\u00e0 t\u1ea1o ra chu\u1ed7i \u0111\u1ea7u ra theo t\u1eebng b\u01b0\u1edbc.<\/li>\n<\/ol>\n<h2>Ph\u00e2n t\u00edch c\u00e1c t\u00ednh n\u0103ng ch\u00ednh c\u1ee7a M\u00f4 h\u00ecnh tu\u1ea7n t\u1ef1 (Seq2Seq)<\/h2>\n<ol>\n<li><strong>H\u1ecdc t\u1eadp t\u1eeb \u0111\u1ea7u \u0111\u1ebfn cu\u1ed1i<\/strong>: N\u00f3 h\u1ecdc c\u00e1ch \u00e1nh x\u1ea1 t\u1eeb c\u00e1c chu\u1ed7i \u0111\u1ea7u v\u00e0o \u0111\u1ebfn \u0111\u1ea7u ra trong m\u1ed9t m\u00f4 h\u00ecnh duy nh\u1ea5t.<\/li>\n<li><strong>Uy\u1ec3n chuy\u1ec3n<\/strong>: C\u00f3 th\u1ec3 \u0111\u01b0\u1ee3c s\u1eed d\u1ee5ng cho c\u00e1c nhi\u1ec7m v\u1ee5 d\u1ef1a tr\u00ean tr\u00ecnh t\u1ef1 kh\u00e1c nhau.<\/li>\n<li><strong>\u0110\u1ed9 ph\u1ee9c t\u1ea1p<\/strong>: Y\u00eau c\u1ea7u \u0111i\u1ec1u ch\u1ec9nh c\u1ea9n th\u1eadn v\u00e0 l\u01b0\u1ee3ng l\u1edbn d\u1eef li\u1ec7u \u0111\u1ec3 hu\u1ea5n luy\u1ec7n.<\/li>\n<\/ol>\n<h2>C\u00e1c lo\u1ea1i m\u00f4 h\u00ecnh tu\u1ea7n t\u1ef1 theo tr\u00ecnh t\u1ef1 (Seq2Seq): S\u1eed d\u1ee5ng b\u1ea3ng v\u00e0 danh s\u00e1ch<\/h2>\n<h3>C\u00e1c bi\u1ebfn th\u1ec3:<\/h3>\n<ul>\n<li><strong>Seq2Seq d\u1ef1a tr\u00ean RNN c\u01a1 b\u1ea3n<\/strong><\/li>\n<li><strong>Seq2Seq d\u1ef1a tr\u00ean LSTM<\/strong><\/li>\n<li><strong>Seq2Seq d\u1ef1a tr\u00ean GRU<\/strong><\/li>\n<li><strong>Seq2Seq d\u1ef1a tr\u00ean s\u1ef1 ch\u00fa \u00fd<\/strong><\/li>\n<\/ul>\n<h3>B\u1ea3ng: So s\u00e1nh<\/h3>\n<table>\n<thead>\n<tr>\n<th>Ki\u1ec3u<\/th>\n<th>\u0110\u1eb7c tr\u01b0ng<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>Seq2Seq d\u1ef1a tr\u00ean RNN c\u01a1 b\u1ea3n<\/td>\n<td>\u0110\u01a1n gi\u1ea3n, d\u1ec5 b\u1ecb bi\u1ebfn m\u1ea5t v\u1ea5n \u0111\u1ec1 \u0111\u1ed9 d\u1ed1c<\/td>\n<\/tr>\n<tr>\n<td>Seq2Seq d\u1ef1a tr\u00ean LSTM<\/td>\n<td>Ph\u1ee9c t\u1ea1p, x\u1eed l\u00fd c\u00e1c ph\u1ee5 thu\u1ed9c d\u00e0i<\/td>\n<\/tr>\n<tr>\n<td>Seq2Seq d\u1ef1a tr\u00ean GRU<\/td>\n<td>T\u01b0\u01a1ng t\u1ef1 nh\u01b0 LSTM nh\u01b0ng hi\u1ec7u qu\u1ea3 h\u01a1n v\u1ec1 m\u1eb7t t\u00ednh to\u00e1n<\/td>\n<\/tr>\n<tr>\n<td>Seq2Seq d\u1ef1a tr\u00ean s\u1ef1 ch\u00fa \u00fd<\/td>\n<td>T\u1eadp trung v\u00e0o c\u00e1c ph\u1ea7n c\u00f3 li\u00ean quan c\u1ee7a \u0111\u1ea7u v\u00e0o trong qu\u00e1 tr\u00ecnh gi\u1ea3i m\u00e3<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>C\u00e1c c\u00e1ch s\u1eed d\u1ee5ng M\u00f4 h\u00ecnh tu\u1ea7n t\u1ef1 (Seq2Seq), c\u00e1c v\u1ea5n \u0111\u1ec1 v\u00e0 gi\u1ea3i ph\u00e1p c\u1ee7a ch\u00fang<\/h2>\n<h3>C\u00f4ng d\u1ee5ng:<\/h3>\n<ul>\n<li><strong>D\u1ecbch m\u00e1y<\/strong><\/li>\n<li><strong>Nh\u1eadn d\u1ea1ng gi\u1ecdng n\u00f3i<\/strong><\/li>\n<li><strong>D\u1ef1 b\u00e1o chu\u1ed7i th\u1eddi gian<\/strong><\/li>\n<\/ul>\n<h3>V\u1ea5n \u0111\u1ec1 &amp; Gi\u1ea3i ph\u00e1p:<\/h3>\n<ul>\n<li><strong>V\u1ea5n \u0111\u1ec1 v\u1ec1 \u0111\u1ed9 d\u1ed1c bi\u1ebfn m\u1ea5t<\/strong>: Gi\u1ea3i quy\u1ebft b\u1eb1ng c\u00e1ch s\u1eed d\u1ee5ng LSTM ho\u1eb7c GRU.<\/li>\n<li><strong>Y\u00eau c\u1ea7u d\u1eef li\u1ec7u<\/strong>: C\u1ea7n b\u1ed9 d\u1eef li\u1ec7u l\u1edbn; c\u00f3 th\u1ec3 \u0111\u01b0\u1ee3c gi\u1ea3m thi\u1ec3u th\u00f4ng qua vi\u1ec7c t\u0103ng c\u01b0\u1eddng d\u1eef li\u1ec7u.<\/li>\n<\/ul>\n<h2>C\u00e1c \u0111\u1eb7c \u0111i\u1ec3m ch\u00ednh v\u00e0 nh\u1eefng so s\u00e1nh kh\u00e1c v\u1edbi c\u00e1c thu\u1eadt ng\u1eef t\u01b0\u01a1ng t\u1ef1<\/h2>\n<h3>B\u1ea3ng: So s\u00e1nh v\u1edbi c\u00e1c m\u1eabu kh\u00e1c<\/h3>\n<table>\n<thead>\n<tr>\n<th>T\u00ednh n\u0103ng<\/th>\n<th>Seq2Seq<\/th>\n<th>M\u1ea1ng th\u1ea7n kinh Feedforward<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>X\u1eed l\u00fd tr\u00ecnh t\u1ef1<\/td>\n<td>\u0110\u00fang<\/td>\n<td>KH\u00d4NG<\/td>\n<\/tr>\n<tr>\n<td>\u0110\u1ed9 ph\u1ee9c t\u1ea1p<\/td>\n<td>Cao<\/td>\n<td>V\u1eeba ph\u1ea3i<\/td>\n<\/tr>\n<tr>\n<td>Y\u00eau c\u1ea7u \u0111\u00e0o t\u1ea1o<\/td>\n<td>T\u1eadp d\u1eef li\u1ec7u l\u1edbn<\/td>\n<td>Kh\u00e1c nhau<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2>C\u00e1c quan \u0111i\u1ec3m v\u00e0 c\u00f4ng ngh\u1ec7 c\u1ee7a t\u01b0\u01a1ng lai li\u00ean quan \u0111\u1ebfn c\u00e1c m\u00f4 h\u00ecnh tu\u1ea7n t\u1ef1 (Seq2Seq)<\/h2>\n<p>T\u01b0\u01a1ng lai c\u1ee7a c\u00e1c m\u00f4 h\u00ecnh Seq2Seq bao g\u1ed3m:<\/p>\n<ul>\n<li><strong>T\u00edch h\u1ee3p v\u1edbi C\u01a1 ch\u1ebf ch\u00fa \u00fd n\u00e2ng cao<\/strong><\/li>\n<li><strong>D\u1ecbch v\u1ee5 d\u1ecbch thu\u1eadt th\u1eddi gian th\u1ef1c<\/strong><\/li>\n<li><strong>Tr\u1ee3 l\u00fd gi\u1ecdng n\u00f3i c\u00f3 th\u1ec3 t\u00f9y ch\u1ec9nh<\/strong><\/li>\n<li><strong>Hi\u1ec7u su\u1ea5t n\u00e2ng cao trong c\u00e1c t\u00e1c v\u1ee5 s\u00e1ng t\u1ea1o<\/strong><\/li>\n<\/ul>\n<h2>C\u00e1ch s\u1eed d\u1ee5ng ho\u1eb7c li\u00ean k\u1ebft m\u00e1y ch\u1ee7 proxy v\u1edbi c\u00e1c m\u00f4 h\u00ecnh tu\u1ea7n t\u1ef1 (Seq2Seq)<\/h2>\n<p>C\u00e1c m\u00e1y ch\u1ee7 proxy nh\u01b0 OneProxy c\u00f3 th\u1ec3 \u0111\u01b0\u1ee3c s\u1eed d\u1ee5ng \u0111\u1ec3 h\u1ed7 tr\u1ee3 vi\u1ec7c \u0111\u00e0o t\u1ea1o v\u00e0 tri\u1ec3n khai c\u00e1c m\u00f4 h\u00ecnh Seq2Seq b\u1eb1ng c\u00e1ch:<\/p>\n<ul>\n<li><strong>Thu th\u1eadp d\u1eef li\u1ec7u<\/strong>: Thu th\u1eadp d\u1eef li\u1ec7u t\u1eeb nhi\u1ec1u ngu\u1ed3n kh\u00e1c nhau m\u00e0 kh\u00f4ng h\u1ea1n ch\u1ebf IP.<\/li>\n<li><strong>C\u00e2n b\u1eb1ng t\u1ea3i<\/strong>: Ph\u00e2n ph\u1ed1i t\u1ea3i t\u00ednh to\u00e1n tr\u00ean nhi\u1ec1u m\u00e1y ch\u1ee7 \u0111\u1ec3 \u0111\u00e0o t\u1ea1o c\u00f3 th\u1ec3 m\u1edf r\u1ed9ng.<\/li>\n<li><strong>B\u1ea3o v\u1ec7 m\u00f4 h\u00ecnh<\/strong>: B\u1ea3o v\u1ec7 c\u00e1c m\u00f4 h\u00ecnh kh\u1ecfi s\u1ef1 truy c\u1eadp tr\u00e1i ph\u00e9p.<\/li>\n<\/ul>\n<h2>Li\u00ean k\u1ebft li\u00ean quan<\/h2>\n<ul>\n<li><a href=\"https:\/\/arxiv.org\/abs\/1409.3215\" target=\"_new\" rel=\"noopener nofollow\">B\u00e0i vi\u1ebft g\u1ed1c c\u1ee7a Google v\u1ec1 Seq2Seq<\/a><\/li>\n<li><a href=\"https:\/\/www.tensorflow.org\/tutorials\/text\/nmt_with_attention\" target=\"_new\" rel=\"noopener nofollow\">H\u01b0\u1edbng d\u1eabn x\u00e2y d\u1ef1ng m\u00f4 h\u00ecnh Seq2Seq<\/a><\/li>\n<li><a href=\"https:\/\/oneproxy.pro\/vn\/\" target=\"_new\" rel=\"noopener\">Trang web OneProxy d\u00e0nh cho c\u00e1c d\u1ecbch v\u1ee5 proxy<\/a><\/li>\n<\/ul>","protected":false},"featured_media":470469,"menu_order":0,"template":"","meta":{"_acf_changed":false,"content-type":"","inline_featured_image":false,"footnotes":""},"class_list":["post-478929","wiki","type-wiki","status-publish","has-post-thumbnail","hentry"],"acf":{"faq_title":"Frequently Asked Questions about <mark>Brief Information about Sequence-to-Sequence Models (Seq2Seq)<\/mark>","faq_items":[{"question":"What are Sequence-to-Sequence models (Seq2Seq)?","answer":"<p>Sequence-to-Sequence models (Seq2Seq) are deep learning models designed to translate sequences from one domain into sequences in another. They consist of an encoder to process the input sequence and a decoder to produce the output sequence, and they have applications in fields like natural language processing and time-series forecasting.<\/p>"},{"question":"What is the historical background of Sequence-to-Sequence models?","answer":"<p>Seq2Seq models were first introduced by researchers from Google in 2014. They described a model using two Recurrent Neural Networks (RNNs): an encoder and a decoder. The concept rapidly gained traction and inspired further research.<\/p>"},{"question":"How do Sequence-to-Sequence models work?","answer":"<p>Seq2Seq models work by processing an input sequence through an encoder, compressing it into a context vector, and then using a decoder to produce the corresponding output sequence. The model is trained to map input to output sequences using algorithms like gradient-based optimization.<\/p>"},{"question":"What are the key features of Sequence-to-Sequence models?","answer":"<p>The key features of Seq2Seq models include end-to-end learning of sequence mappings, flexibility in handling various sequence-based tasks, and complexity in design that requires careful tuning and large datasets.<\/p>"},{"question":"What types of Sequence-to-Sequence models exist?","answer":"<p>There are several types of Seq2Seq models, including basic RNN-based, LSTM-based, GRU-based, and Attention-based Seq2Seq models. Each variant offers unique features and benefits.<\/p>"},{"question":"What are the common ways to use Seq2Seq models, and what problems might arise?","answer":"<p>Seq2Seq models are used in machine translation, speech recognition, and time-series forecasting. Common problems include the vanishing gradient problem and the need for large datasets, which can be mitigated through specific techniques like using LSTMs or data augmentation.<\/p>"},{"question":"How do Sequence-to-Sequence models compare to other similar models?","answer":"<p>Seq2Seq models are distinct in handling sequences, whereas other models like feedforward neural networks might not handle sequences. Seq2Seq models are generally more complex and require large datasets for training.<\/p>"},{"question":"What are the future prospects of Sequence-to-Sequence models?","answer":"<p>The future of Seq2Seq models includes integration with advanced attention mechanisms, real-time translation services, customizable voice assistants, and enhanced performance in generative tasks.<\/p>"},{"question":"How can proxy servers like OneProxy be used with Sequence-to-Sequence models?","answer":"<p>Proxy servers like OneProxy can facilitate the training and deployment of Seq2Seq models by assisting in data collection, load balancing, and securing models. They help in gathering data from various sources, distributing computational loads, and protecting models from unauthorized access.<\/p>"}]},"_links":{"self":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/wiki\/478929","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/wiki"}],"about":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/types\/wiki"}],"version-history":[{"count":0,"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/wiki\/478929\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/media\/470469"}],"wp:attachment":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/media?parent=478929"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}