-
公开(公告)号：US20170371868A1
公开(公告)日：2017-12-28
申请号：US15192109
申请日：2016-06-24
Applicant: Facebook, Inc.
Inventor： Ying Zhang , Fei Huang , Kay Rottmann , Necip Fazil Ayan
CPC classification number: G06F17/2854 , G06F17/2818 , G06F17/289 , G06Q50/01
Abstract: Exemplary embodiments relate to techniques for improving a machine translation system. The machine translation system may include one or more models for generating a translation. The system may generate multiple candidate translations, and may present the candidate translations to different groups of users, such as users of a social network. User engagement with the different candidate translations may be measured, and the system may determine which of the candidate translations was most favored by the users. For example, in the context of a social network, the number of times that the translation is liked or shared, or the number of comments associated with the translation, may be used to determine user engagement with the translation. The models of the machine translation system may be modified to favor the most-favored candidate translation. The translation system may repeat this process to continue to tune the models in a feedback loop.
-
公开(公告)号：US09805029B2
公开(公告)日：2017-10-31
申请号：US14981794
申请日：2015-12-28
Applicant: Facebook, Inc.
Inventor： Kay Rottmann , Fei Huang , Ying Zhang
CPC classification number: G06F17/289 , G06F17/2854
Abstract: Technology is disclosed for snippet pre-translation and dynamic selection of translation systems. Pre-translation uses snippet attributes such as characteristics of a snippet author, snippet topics, snippet context, expected snippet viewers, etc., to predict how many translation requests for the snippet are likely to be received. An appropriate translator can be dynamically selected to produce a translation of a snippet either as a result of the snippet being selected for pre-translation or from another trigger, such as a user requesting a translation of the snippet. Different translators can generate high quality translations after a period of time or other translators can generate lower quality translations earlier. Dynamic selection of translators involves dynamically selecting machine or human translation, e.g., based on a quality of translation that is desired. Translations can be improved over time by employing better machine or human translators, such as when a snippet is identified as being more popular.
-
13.发明申请PROVIDING TRANSLATIONS OF ELECTRONIC MESSAGES VIA A SOCIAL NETWORKING SYSTEM 审中-公开通过社会网络系统提供电子信息的翻译公开(公告)号：US20160191448A1
公开(公告)日：2016-06-30
申请号：US14588078
申请日：2014-12-31
Applicant: FACEBOOK, INC.
Inventor： Matthias Eck , Necip Fazil Ayan , Ying Zhang , Kay Rottman , Lukasz Langa
IPC: H04L12/58
CPC classification number: H04L51/32 , H04L51/063
Abstract: The present disclosure is directed toward systems and methods for providing translations of electronic messages via a social networking system. For example, systems and methods described herein involve determining whether to provide an electronic message or a translation of the electronic message to a recipient based on social networking activities of the recipient. Furthermore, systems and methods described herein can provide a translation of an electronic message based on an analysis of social networking activities of one or more recipients of the electronic message.
Abstract translation: 本公开涉及通过社交网络系统提供电子消息的翻译的系统和方法。 例如，本文描述的系统和方法涉及基于接收者的社交网络活动确定是否向接收者提供电子消息或电子消息的翻译。 此外，本文描述的系统和方法可以基于对电子消息的一个或多个接收者的社交网络活动的分析来提供电子消息的翻译。
-
公开(公告)号：US11195106B2
公开(公告)日：2021-12-07
申请号：US15636390
申请日：2017-06-28
Applicant: Facebook, Inc.
Inventor： Shengbo Guo , Mark Warren McDuff , Yixian Zhu , Ying Zhang , James Li , Sara Lee Su
Abstract: Systems, methods, and non-transitory computer readable media are configured to receive a uniform resource locator. A time and one or more features associated with the uniform resource locator can be provided to a first machine learning model. A prediction relating to a quantity of views the uniform resource locator achieves by the time can be received from the first machine learning model.
-
15.发明授权公开(公告)号：US10528677B1
公开(公告)日：2020-01-07
申请号：US16281974
申请日：2019-02-21
Applicant: Facebook, Inc.
Inventor： Ying Zhang , Alexander Waibel
Abstract: A social networking system determines whether a particular user is qualified to provide translations of text from a first language to a second language. The determination may include evaluation of the language competencies of the user, and also of the trustworthiness of the user as a translator, as determined based on prior translations submitted by the user. The social networking system also selects translations of a text item for a user to whom that text is to be shown. When evaluating a candidate translation for presentation to the user, the evaluation may assess factors such as the determined qualification as a translator of the user who provided the candidate translation; a quality score of the candidate translation itself; and/or the similarity of the user viewing the content and the user providing the candidate translation.
-
Patent Agency Ranking
公开(公告)号：US20190095869A1
公开(公告)日：2019-03-28
申请号：US15718630
申请日：2017-09-28
Applicant: Facebook, Inc.
Inventor： Ying Zhang , Wenzhe Jiang , Lei Sun , Zain Rehmani , Cheng Yang , Gaurav Dosi
Abstract: Exemplary embodiments relate to techniques for identifying job seekers in a platform, such as a social networking or messaging service, and presenting the job seekers with job postings that they are most likely to be interested in. The job seeker's intent may be determined based on various factors. The system may rank job postings by the probability that a user will be interested in a particular job, and can surface jobs to the user in a number of ways. Applicable jobs can be surfaced in an interactable list. If the user interacts with the list, then the system may determine that the user is a job seeker and that the posted jobs are in their field of interest; otherwise, one of those elements is considered to be missing and the system may adjust its approach
-
公开(公告)号：US20190095868A1
公开(公告)日：2019-03-28
申请号：US15718601
申请日：2017-09-28
Applicant: Facebook, Inc.
Inventor： Ying Zhang , Wenzhe Jiang , Lei Sun , Zain Rehmani , Cheng Yang , Gaurav Dosi
Abstract: Exemplary embodiments relate to techniques for identifying job listing posts in a platform, such as a social networking or messaging service. Job listing posts can be identified as they are created, causing the user to enter a job posting interface for entering structured data. The structured data may be searchable on the platform. Job posts can also be identified post hoc, and subsequently converted to structured job listing posts. Structured information may be drawn from the freeform text, and the system may normalize the job description (e.g., using third-party information, such as standard job descriptors). Identifying a job listing post/intent may be done using a model trained using various parameters, such as: user feedback/administrator actions; corrections; content of the post; existing posts of page owner; the time of year; whether other employers in similar fields are post job openings; and whether this owner prefers to write structured or unstructured posts.
-
公开(公告)号：US20190012315A1
公开(公告)日：2019-01-10
申请号：US15886817
申请日：2018-02-01
Applicant: Facebook, Inc.
Inventor： Ying Zhang , Fei Huang
Abstract: A machine translation system can improve results of machine translations by employing preferred translations, such as human translated phrases. In some implementations, the machine translation system can use the preferred translations as heavily weighted training data when building a machine translation engine. In some implementations, the machine translation system can use the preferred translations as an alternate to a result that would have otherwise been produced by a machine translation engine. While it is infeasible to obtain human translations for all translation phrases, preferred translations can be used for problem phrases for which machine translation engines often produce poor translations. The machine translation system can identify problem phrases by assigning a quality score to each translation in a set of translations. The machine translation system can identify, as the problem phrases, n-grams that appear with a frequency above a frequency threshold in translations with quality scores below a threshold.
-
公开(公告)号：US10002125B2
公开(公告)日：2018-06-19
申请号：US14980654
申请日：2015-12-28
Applicant: Facebook, Inc.
Inventor： Juan Miguel Pino , Ying Zhang , Matthias Gerhard Eck
CPC classification number: G06F17/2735 , G06F17/2775 , G06F17/2836 , G06F17/2845 , G06N7/005 , G06N20/00
Abstract: Specialized language processing engines can use author-specific or reader-specific language models to improve language processing results by selecting phrases most likely to be used by an author or by tailoring output to language with which the reader is familiar. Language models that are author-specific can be generated by identifying characteristics of an author or author type such as age, gender, and location. An author-specific language model can be built using, as training data, language items written by users with the identified characteristics. Language models that are reader-specific can be generated using, as training data, language items written by or viewed by that reader. When implementing a specialized machine translation engine, multiple possible translations can be generated. An author-specific language model or a reader-specific language model can provide scores for possible translations, which can be used to select the best translation.
-
公开(公告)号：US09922029B1
公开(公告)日：2018-03-20
申请号：US15221365
申请日：2016-07-27
Applicant: Facebook, Inc.
Inventor： Ying Zhang , Fei Huang
CPC classification number: G06F17/2854 , G06F17/274 , G06F17/2765 , G06F17/2836
Abstract: A machine translation system can improve results of machine translations by employing preferred translations, such as human translated phrases. In some implementations, the machine translation system can use the preferred translations as heavily weighted training data when building a machine translation engine. In some implementations, the machine translation system can use the preferred translations as an alternate to a result that would have otherwise been produced by a machine translation engine. While it is infeasible to obtain human translations for all translation phrases, preferred translations can be used for problem phrases for which machine translation engines often produce poor translations. The machine translation system can identify problem phrases by assigning a quality score to each translation in a set of translations. The machine translation system can identify, as the problem phrases, n-grams that appear with a frequency above a frequency threshold in translations with quality scores below a threshold.
-
-
-
-
-
-
-
-
-
Search Results
71
records
(took 0.024 seconds)
