公开(公告)号：US20200027034A1

公开(公告)日：2020-01-23

申请号：US16041073

申请日：2018-07-20

Applicant: Oath Inc.

Inventor： Siddhartha Banerjee ,  Kostas Tsioutsiouliklis

IPC: G06N99/00 ,  G06F17/27

Abstract: The present teaching relates to method, system, and medium for generating training data for generating a relationship identification model. Sentences are received as input. Each of the sentences is aligned with a fact previously stored to create an alignment. Confidence scores for the alignments are computed and then used, together with the alignments to train a relationship identification model.

公开(公告)号：US10902350B2

公开(公告)日：2021-01-26

申请号：US16041073

申请日：2018-07-20

Applicant: Oath Inc.

Inventor： Siddhartha Banerjee ,  Kostas Tsioutsiouliklis

IPC: G06F40/30 ,  G06N20/00 ,  G06F40/253 ,  G06F40/295

Abstract: The present teaching relates to method, system, and medium for generating training data for generating a relationship identification model. Sentences are received as input. Each of the sentences is aligned with a fact previously stored to create an alignment. Confidence scores for the alignments are computed and then used, together with the alignments to train a relationship identification model.

公开(公告)号：US10832008B2

公开(公告)日：2020-11-10

申请号：US16217195

申请日：2018-12-12

Applicant: OATH INC.

Inventor： Siddhartha Banerjee ,  Prakhar Biyani ,  Kostas Tsioutsiouliklis

IPC: G06F40/20 ,  G06F40/35 ,  H04L12/58 ,  G06F40/205 ,  G06F40/253 ,  G06F40/284 ,  H04L29/08

Abstract: Disclosed are systems and methods for improving interactions with and between computers in content searching, generating, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The disclosure provides a computerized framework for automatically generating chatbot responses to produce domain-specific responses that mimic native styles unique to particular domains. The disclosed systems and methods construct domain-specific word-graphs based on account activity from specific domains and generate word-patterns. New words obtained from the patterns in the graph are introduced to transform the regular response. The graph is then pruned using data-driven thresholds in order to avoid spurious transformations, and paragraph vectors are also utilized to assign relevance scores to generated patterns such that only the patterns that are contextually similar to the original response (generic/regular response) are used. As result, the regular chatbot response is rewritten using an optimized set of patterns.

公开(公告)号：US10162816B1

公开(公告)日：2018-12-25

申请号：US15623668

申请日：2017-06-15

Applicant: OATH INC.

Inventor： Siddhartha Banerjee ,  Prakhar Biyani ,  Kostas Tsioutsiouliklis

IPC: G06F17/27 ,  H04L29/08 ,  H04L12/58

Abstract: Disclosed are systems and methods for improving interactions with and between computers in content searching, generating, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The disclosure provides a computerized framework for automatically generating chatbot responses to produce domain-specific responses that mimic native styles unique to particular domains. The disclosed systems and methods construct domain-specific word-graphs based on account activity from specific domains and generate word-patterns. New words obtained from the patterns in the graph are introduced to transform the regular response. The graph is then pruned using data-driven thresholds in order to avoid spurious transformations, and paragraph vectors are also utilized to assign relevance scores to generated patterns such that only the patterns that are contextually similar to the original response (generic/regular response) are used. As result, the regular chatbot response is rewritten using an optimized set of patterns.