发明名称 TECHNIQUES FOR PERFORMING LANGUAGE DETECTION AND TRANSLATION FOR MULTI-LANGUAGE CONTENT FEEDS
摘要 A technique for translating a portion of a website includes receiving a language set of a user indicating a primary language of the user is received. A content feed to be displayed to the user is received and parsed to identify a text portion of a user generated content. The original language of the text portion is determined and compared with the one or more languages in the language set. When the original language of the text portion does not match the languages in the language set: (i) the text portion, the original language, and the primary language are provided to a translation engine, (ii) a translated version of the text portion is received from the translation engine, (iii) the translated version of the text portion is inserted into the content feed to obtain a modified content feed, and (iv) the modified content feed is displayed to the user.
申请公布号 US2014350916(A1) 申请公布日期 2014.11.27
申请号 US201414458685 申请日期 2014.08.13
申请人 Google Inc. 发明人 Swerdlow Andrew;Jagpal Navdeep Singh
分类号 G06F17/28;G06F17/27 主分类号 G06F17/28
代理机构 代理人
主权项 1. A computer-implemented method, comprising: obtaining, at a computing device having one or more processors, a parsable content feed from at least one server associated with a social network, the parsable content feed comprising at least one of (i) user-generated text posts on the social network and (ii) user-generated text comments to posts on the social network; obtaining, at the computing device, a set of preferred languages for a user operating the computing device; identifying, at the computing device, a text portion in the parsable content feed; obtaining, at the computing device, a detected language for the text portion; comparing, at the computing device, the detected language to the set of preferred languages; when the detected language does not match any of the set of preferred languages, obtaining, at the computing device, a machine translation of the text portion from the detected language to one of the set of preferred languages; and outputting, at the computing device, the machine translation of the text portion.
地址 Mountain View CA US