{"id":1225,"date":"2021-12-22T06:00:00","date_gmt":"2021-12-21T21:00:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=1225"},"modified":"2021-12-22T06:00:00","modified_gmt":"2021-12-21T21:00:00","slug":"katknowledge-augmented-transformer-%e7%94%bb%e5%83%8f-%e8%a8%80%e8%aa%9e%e7%94%a8%e3%81%ae%e5%a4%96%e9%83%a8%e7%9f%a5%e8%ad%98%e6%b4%bb%e7%94%a8","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=1225","title":{"rendered":"KAT(Knowledge Augmented Transformer): \u753b\u50cf\/\u8a00\u8a9e\u7528\u306e\u5916\u90e8\u77e5\u8b58\u6d3b\u7528"},"content":{"rendered":"\n<ul class=\"wp-block-list\"><li><strong>KAT: A Knowledge Augmented Transformer for Vision-and-Language\u00a0<\/strong>[56.7]<br>\u6211\u3005\u306f\u3001OK-VQA\u306e\u30aa\u30fc\u30d7\u30f3\u30c9\u30e1\u30a4\u30f3\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u30bf\u30b9\u30af\u306b\u304a\u3044\u3066\u3001\u6700\u5148\u7aef\u306e\u5f37\u529b\u306a\u7d50\u679c\u3092\u3082\u305f\u3089\u3059\u65b0\u3057\u3044\u30e2\u30c7\u30eb\u3067\u3042\u308b\u77e5\u8b58\u62e1\u5f35\u30c8\u30e9\u30f3\u30b9\u30d5\u30a9\u30fc\u30de\u30fc(KAT)\u3092\u63d0\u6848\u3059\u308b\u3002 \u63d0\u6848\u624b\u6cd5\u306f,\u30a8\u30f3\u30c9\u30fb\u30c4\u30fc\u30fb\u30a8\u30f3\u30c9\u306e\u30a8\u30f3\u30b3\u30fc\u30c0\u30fb\u30c7\u30b3\u30fc\u30c0\u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3\u306b\u304a\u3044\u3066\u6697\u9ed9\u7684\u304b\u3064\u660e\u793a\u7684\u306a\u77e5\u8b58\u3092\u7d71\u5408\u3057\u3064\u3064,\u56de\u7b54\u751f\u6210\u6642\u306b\u4e21\u77e5\u8b58\u6e90\u3092\u5171\u540c\u3067\u63a8\u8ad6\u3059\u308b\u3002 \u6211\u3005\u306e\u5206\u6790\u3067\u306f\u3001\u30e2\u30c7\u30eb\u4e88\u6e2c\u306e\u89e3\u91c8\u53ef\u80fd\u6027\u306e\u5411\u4e0a\u306b\u3001\u660e\u793a\u7684\u306a\u77e5\u8b58\u7d71\u5408\u306e\u3055\u3089\u306a\u308b\u5229\u70b9\u304c\u898b\u3089\u308c\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2112.08614v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2112.08614v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Thu, 16 Dec 2021 04:37:10 GMT)<ul><li>Explicit knowledge\u3092Wikipedia\u306a\u3069\u306e\u30ea\u30bd\u30fc\u30b9\u304b\u3089\u3001Implicit knowledge\u3092GPT-3\u304b\u3089\u53d6\u308a\u51fa\u3057\u3066\u7d71\u5408\u3001\u8cea\u554f\u306b\u56de\u7b54\u3059\u308b\u624b\u6cd5\u306e\u63d0\u6848\u3002<a href=\"https:\/\/okvqa.allenai.org\/leaderboard.html\">OK-VQA (allenai.org)<\/a>\u3067\u65e2\u5b58\u306eSoTA\u3092\u5927\u5e45\u306b\u66f4\u65b0\u3068\u306e\u3053\u3068\u3002<\/li><li>\u30a2\u30d7\u30ed\u30fc\u30c1\u306f\u8ad6\u65874\u30da\u30fc\u30b8\u306e\u56f3\u304c\u5206\u304b\u308a\u3084\u3059\u304f\uff08\u305d\u308c\u3067\u3082\u8907\u96d1\u3060\u304c\uff09\u3001\u65e2\u5b58\u30e2\u30b8\u30e5\u30fc\u30eb\u3092\u7d44\u307f\u5408\u308f\u305b\u3066\u30d1\u30a4\u30d7\u30e9\u30a4\u30f3\u3092\u7d44\u3093\u3067\u3044\u308b\u3002<\/li><\/ul><\/li><\/ul>\n","protected":false},"excerpt":{"rendered":"<p>KAT: A Knowledge Augmented Transformer for Vision-and-Language\u00a0[56.7]\u6211\u3005\u306f\u3001OK-VQA\u306e\u30aa\u30fc\u30d7\u30f3\u30c9\u30e1\u30a4\u30f3\u30de\u30eb\u30c1\u30e2\u30fc\u30c0\u30eb\u30bf\u30b9\u30af\u306b\u304a\u3044\u3066\u3001\u6700\u5148\u7aef\u306e\u5f37\u529b\u306a &hellip; <a href=\"https:\/\/devneko.jp\/wordpress\/?p=1225\" class=\"more-link\"><span class=\"screen-reader-text\">&#8220;KAT(Knowledge Augmented Transformer): \u753b\u50cf\/\u8a00\u8a9e\u7528\u306e\u5916\u90e8\u77e5\u8b58\u6d3b\u7528&#8221; \u306e<\/span>\u7d9a\u304d\u3092\u8aad\u3080<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[415,436,441],"class_list":["post-1225","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-transformer","tag-visual-question-answering","tag-vqa"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1225","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1225"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1225\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1225"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1225"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1225"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}