公开(公告)号：US20200320370A1

公开(公告)日：2020-10-08

申请号：US16857958

申请日：2020-04-24

Applicant: eBay Inc.

Inventor： Chandra Prakash Khatri ,  Nish Parikh ,  Sameep Navin Solanki ,  Justin Nicholas House ,  Gyanit Singh

IPC: G06N3/04 ,  G06F16/34

Abstract: Systems, methods and media are provided for training a snippet extractor to create snippets based on information extracted from published descriptions. In one example, a computer-implemented method includes creating, based on a non-RNN (Recurrent Neural Network) extraction technique performed on the published descriptions, a plurality of base models, each base model including one or more sample description summaries; evaluating the base models using an evaluation technique; selecting an optimum base model; developing a classification model using RNN extraction, the classification model based on description summaries contained in the optimum base model; and using the classification model to train the snippet extractor by machine learning.

公开(公告)号：US20180046611A1

公开(公告)日：2018-02-15

申请号：US15237091

申请日：2016-08-15

Applicant: eBay Inc.

Inventor： Chandra Prakash Khatri ,  Selcuk Kopru ,  Nish Parikh ,  Justin Nicholas House ,  Sameep Navin Solanki

IPC: G06F17/27 ,  G06F17/24 ,  G06F17/30

CPC classification number: G06F17/277 ,  G06F16/3349 ,  G06F16/345 ,  G06F16/374 ,  G06F17/241 ,  G06F17/2735

Abstract: In various example embodiments, a system and method for a Target Language Engine are presented. The Target Language Engine augments a synonym list in a base dictionary of a target language with one or more historical search queries previously submitted to search one or more listings in listing data. The Target Language Engine identifies a compound word and a plurality of words present in the listing data that have a common meaning in the target language. Each word from the plurality of words is present in the compound word. The Target Language Engine causes a database to create an associative link between the portion of text and a word selected from at least one of the synonym list or the plurality of words.

公开(公告)号：US10521509B2

公开(公告)日：2019-12-31

申请号：US15237091

申请日：2016-08-15

Applicant: eBay Inc.

Inventor： Chandra Prakash Khatri ,  Selcuk Kopru ,  Nish Parikh ,  Justin Nicholas House ,  Sameep Navin Solanki

IPC: G06F17/27 ,  G06F17/24 ,  G06F16/36 ,  G06F16/33 ,  G06F16/34

Abstract: In various example embodiments, a system and method for a Target Language Engine are presented. The Target Language Engine augments a synonym list in a base dictionary of a target language with one or more historical search queries previously submitted to search one or more listings in listing data. The Target Language Engine identifies a compound word and a plurality of words present in the listing data that have a common meaning in the target language. Each word from the plurality of words is present in the compound word. The Target Language Engine causes a database to create an associative link between the portion of text and a word selected from at least one of the synonym list or the plurality of words.

公开(公告)号：US20190354532A1

公开(公告)日：2019-11-21

申请号：US16531929

申请日：2019-08-05

Applicant: eBay Inc.

Inventor： Sameep Navin Solanki ,  Jayasimha Katukuri ,  Manas Haribhai Somaiya ,  Rajyashree Mukherjee ,  Rakesh Setty

IPC: G06F16/2457 ,  G06K9/00 ,  H04N13/261 ,  G06T15/20 ,  G06Q30/08 ,  G06Q30/06 ,  G06T7/20

Abstract: The present disclosure is directed to apparatuses, systems, and methods for enhancing search results based on recent user interactions. As described herein, embodiments may infer various refinements for search queries; these refinements are based, at least in part, on the user's recent interactions with the search platform (e.g., within a current session). In other words, as the user is interacting with the search platform, one or more refinements may be inferred to help make the search results more relevant to the user.

公开(公告)号：US20170213130A1

公开(公告)日：2017-07-27

申请号：US15267346

申请日：2016-09-16

Applicant: eBay Inc.

Inventor： Chandra Prakash Khatri ,  Nish Parikh ,  Sameep Navin Solanki ,  Justin Nicholas House ,  Gyanit Singh

IPC: G06N3/08 ,  G06N3/04 ,  G06F17/30

CPC classification number: G06N3/0445 ,  G06F16/345

Abstract: Systems, methods and media are provided for training a snippet extractor to create snippets based on information extracted from published descriptions. In one example, a computer-implemented method includes creating, based on a non-RNN (Recurrent Neural Network) extraction technique performed on the published descriptions, a plurality of base models, each base model including one or more sample description summaries; evaluating the base models using an evaluation technique; selecting an optimum base model; developing a classification model using RNN extraction, the classification model based on description summaries contained in the optimum base model; and using the classification model to train the snippet extractor by machine learning.

公开(公告)号：US11275746B2

公开(公告)日：2022-03-15

申请号：US16531929

申请日：2019-08-05

Applicant: eBay Inc.

Inventor： Sameep Navin Solanki ,  Jayasimha Katukuri ,  Manas Haribhai Somaiya ,  Rajyashree Mukherjee ,  Rakesh Setty

IPC: G06F16/2457 ,  G06Q30/06 ,  G06Q30/08 ,  H04N13/261 ,  G06K9/00 ,  G06T7/20 ,  G06T15/20

Abstract: The present disclosure is directed to apparatuses, systems, and methods for enhancing search results based on recent user interactions. As described herein, embodiments may infer various refinements for search queries; these refinements are based, at least in part, on the user's recent interactions with the search platform (e.g., within a current session). In other words, as the user is interacting with the search platform, one or more refinements may be inferred to help make the search results more relevant to the user.

公开(公告)号：US20210056265A1

公开(公告)日：2021-02-25

申请号：US17092509

申请日：2020-11-09

Applicant: eBay Inc.

Inventor： Chandra Prakash Khatri ,  Selcuk Kopru ,  Nish Parikh ,  Justin Nicholas House ,  Sameep Navin Solanki

IPC: G06F40/284 ,  G06F16/36 ,  G06F16/33 ,  G06F16/34 ,  G06F40/169 ,  G06F40/242

Abstract: In various example embodiments, a system and method for a Target Language Engine are presented. The Target Language Engine augments a synonym list in a base dictionary of a target language with one or more historical search queries previously submitted to search one or more listings in listing data. The Target Language Engine identifies a compound word and a plurality of words present in the listing data that have a common meaning in the target language. Each word from the plurality of words is present in the compound word. The Target Language Engine causes a database to create an associative link between the portion of text and a word selected from at least one of the synonym list or the plurality of words.