Fei X Huang

20190180386, Jun 13, 2019

Dec 11, 2017

15/838292

- Menlo Park CA, US
Do Huy Hoang - New York NY, US
Yaniv Shmueli - Millburn NJ, US
Fei Huang - Chatham NJ, US

G06Q 50/00
G06Q 30/02
G06F 17/30
G06N 99/00

In one embodiment, a method includes accessing a place-entities graph comprising place-entity nodes, each place-entity node representing a place-entity corresponding to a particular geographic location; identifying a place-entity cluster within the place-entities graph, wherein the place-entity cluster includes place-entity nodes corresponding to respective place-entities each corresponding to the same geographic location; accessing embeddings representing the respective place-entities corresponding to the place-entity cluster; calculating, using a machine-learning model, a cluster-quality score of the place-entity cluster based on the embeddings representing the place-entities corresponding to the place-entity cluster, wherein the cluster-quality score represents a probability that the place-entities corresponding to the place-entity cluster correspond to a valid geographic location; and identifying the place-entities corresponding to the place-entity cluster as corresponding to an invalid geographic location based on a determining that the cluster-quality score is less than a threshold cluster-quality score.

20190012315, Jan 10, 2019

Feb 1, 2018

15/886817

- Menlo Park CA, US
Fei Huang - Boonton NJ, US

G06F 17/28
G06F 17/27

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.

20180139293, May 17, 2018

Nov 17, 2016

15/354592

- Menlo Park CA, US
Taylor Gordon - New York NY, US
Fei Huang - New York NY, US
Jan Kalis - New York NY, US
Justin T. Moore - Brooklyn NY, US
Lars Seren Backstrom - Mountain View CA, US

H04L 29/08
H04L 12/58
G06F 17/30
G06N 99/00

Systems, methods, and non-transitory computer-readable media can generate a set of candidate content items from a plurality of content items that are available in the social networking system for a first user. A corresponding score for each of the candidate content items can be generated based at least in part on one or more social affinity coefficients corresponding to the first user and a respective second user associated with a candidate content item, wherein a social affinity coefficient provides a quantitative measurement of the strength of a relationship between two users. A first set of content items from the set of candidate content items can be determined based at least in part on the respective scores, wherein content items in the first set are included in a content feed provided to the first user.

20180113851, Apr 26, 2018

Aug 9, 2017

15/672690

- Menlo Park CA, US
Fei Huang - Boonton NJ, US

G06F 17/27
G06F 17/21
G06F 17/28

A likely source language of a media item can be identified by attempting an initial language identification of the media item based on intrinsic or extrinsic factors, such as words in the media item and languages known by the media item author. This initial identification can generate a list of most likely source languages with corresponding likelihood factors. Translations can then be performed presuming each of the most likely source languages. The translations can be performed for multiple output languages. Each resulting translation can receive a corresponding score based on a number of factors. The scores can be combined where they have a common source language. These combined scores can be used to weight the previously identified likelihood factors for the source languages of the media item.

20180004734, Jan 4, 2018

Sep 5, 2017

15/696121

- Menlo Park CA, US
Fei Huang - Boonton NJ, US
Ying Zhang - Turlock CA, US

G06F 17/28
G06F 17/27

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.

20170371868, Dec 28, 2017

Jun 24, 2016

15/192109

- Menlo Park CA, US
Fei Huang - Chatham NJ, US
Kay Rottmann - San Francisco CA, US
Necip Fazil Ayan - Menlo Park CA, US

Facebook, Inc. - Menlo Park CA

G06F 17/28
G06Q 50/00

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.

20170315991, Nov 2, 2017

Jul 19, 2017

15/654668

- Menlo Park CA, US
Fei Huang - Boonton NJ, US
Ying Zhang - Turlock CA, US

G06F 17/28
G06F 17/27
G06F 17/28
G06F 17/28

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.

20170185586, Jun 29, 2017

Dec 28, 2015

14/981794

- Menlo Park CA, US
Fei Huang - Boonton NJ, US
Ying Zhang - Turlock CA, US

G06F 17/28
G06F 17/27
G06N 7/00

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.