{"id":263,"date":"2010-04-19T18:54:41","date_gmt":"2010-04-19T23:54:41","guid":{"rendered":"http:\/\/scripts.mit.edu\/~zong\/wpress\/?p=263"},"modified":"2010-04-20T12:39:39","modified_gmt":"2010-04-20T17:39:39","slug":"google-stuck-in-nlp-uncanny-valley","status":"publish","type":"post","link":"https:\/\/blog.yhuang.org\/?p=263","title":{"rendered":"Google stuck in NLP uncanny valley"},"content":{"rendered":"<table border=0 cellpadding=10px width=350 align=\"left\">\n<tr>\n<td><a href=\"wp-content\/uploads\/images\/googlecnmap.png\"><img decoding=\"async\" src=\"wp-content\/uploads\/images\/googlecnmap.png\" width=\"300\" \/><\/a><\/td>\n<\/tr>\n<\/table>\n<p>Google Maps (China) tries automated toponym translation and fails.<\/p>\n<p>Putting aside the question of how useful street-level translation really is for tourists rather than, say, conquerors (if you can&#8217;t read local language maps, how will you read the street signs?), this is actually 80% of the way there for pure transliteration items (a bit stilted). The main problems, in red circles, come from compound toponyms with attached literal meanings (X Pond, X Hill, X Course, Old X, etc.) or with target-language conventions already (Massachusetts X, Oxford X, etc.). Those require translation rather than transliteration, and there the Google bot enters <a href=\"http:\/\/en.wikipedia.org\/wiki\/Uncanny_valley\">uncanny valley<\/a> with its vain attempts, which <a href=\"http:\/\/translate.google.com\/translate?hl=en&#038;sl=zh-CN&#038;tl=en&#038;u=http%3A%2F%2Fwww.google.com%2Fsupport%2Fforum%2Fp%2Fmaps%2Fthread%3Ftid%3D1a75de0be470a5ef%26hl%3Dzh-TW\" target=\"_top\">bothers<\/a> people a lot.<\/p>\n<p>All in all, there were only a few true full-blown errors. One was &#8220;Boston College&#8221;, which got translated as the phrase used for &#8220;Boston University&#8221;. Another was &#8220;Fort Independence&#8221;, which was just wrong to be carried with no syntactical change into Chinese. &#8220;General Edward Lawrence Logan&#8221; was parsed very badly, resulting in a transliteration of &#8220;General&#8221; as if some kind of Hispanic first name.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Google Maps (China) tries automated toponym translation and fails. Putting aside the question of how useful street-level translation really is for tourists rather than, say, conquerors (if you can&#8217;t read local language maps, how will you read the street signs?), this is actually 80% of the way there for pure transliteration items (a bit stilted). [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[1824,418,416,414,413,420,415,421,419,417],"class_list":["post-263","post","type-post","status-publish","format-standard","hentry","category-uncategorized","tag-boston","tag-compound","tag-language-conventions","tag-language-maps","tag-maps-china","tag-street","tag-target-language","tag-toponym","tag-translation","tag-vain-attempts"],"_links":{"self":[{"href":"https:\/\/blog.yhuang.org\/index.php?rest_route=\/wp\/v2\/posts\/263","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blog.yhuang.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blog.yhuang.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blog.yhuang.org\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/blog.yhuang.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=263"}],"version-history":[{"count":0,"href":"https:\/\/blog.yhuang.org\/index.php?rest_route=\/wp\/v2\/posts\/263\/revisions"}],"wp:attachment":[{"href":"https:\/\/blog.yhuang.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=263"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blog.yhuang.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=263"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blog.yhuang.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=263"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}