Sequence to sequence to classification model for generating recommended messages
First Claim
1. A method comprising:
- receiving a first message being transmitted as part of communication session, the first message including a plurality of sequenced words;
generating, using a sequence to sequence encoder included in a sequence to sequence to classification model, a first embedding vector representing the plurality of sequenced words included in the first message the sequence to sequence to classification model including the sequence to sequence encoder and a text classification model, the sequence encoder having been trained based on historical message data that includes messages transmitted between users of a messaging system and the text classification model having been trained based on embedding vectors generated by the sequence to sequence encoder from the historical message data;
generating a feature vector based on the first embedding vector and at least a first feature that is not included in the first embedding vector;
generating a set of candidate responses for replying to the first message by using the feature vector as input into the text classification model, the set of candidate responses being a subset of a set of available responses;
selecting, from the set of candidate responses, a set of recommended responses to the first message, the set of recommended responses being a subset of the set of candidate responses; and
causing the set of recommended responses to be presented by a client device of a recipient user of the first message.
1 Assignment
0 Petitions
Accused Products
Abstract
Disclosed are systems, methods, and non-transitory computer-readable media for a sequence to sequence to classification model for generating recommended messages. A messaging system generates, using a sequence to sequence encoder, an embedding vector from a message being transmitted as part of a communication session, the sequence to sequence encoder having been trained based on historical message data that includes messages transmitted between users of the messaging system. The messaging system determines, based on the embedding vector, a set of candidate responses for replying to the first message, the set of candidate responses being a subset of a set of available responses. The messaging system selects, from the set of candidate responses, a set of recommended responses to the first message, and causes the set of recommended responses to be presented by a client device of a recipient user of the first message.
103 Citations
18 Claims
-
1. A method comprising:
-
receiving a first message being transmitted as part of communication session, the first message including a plurality of sequenced words; generating, using a sequence to sequence encoder included in a sequence to sequence to classification model, a first embedding vector representing the plurality of sequenced words included in the first message the sequence to sequence to classification model including the sequence to sequence encoder and a text classification model, the sequence encoder having been trained based on historical message data that includes messages transmitted between users of a messaging system and the text classification model having been trained based on embedding vectors generated by the sequence to sequence encoder from the historical message data; generating a feature vector based on the first embedding vector and at least a first feature that is not included in the first embedding vector; generating a set of candidate responses for replying to the first message by using the feature vector as input into the text classification model, the set of candidate responses being a subset of a set of available responses; selecting, from the set of candidate responses, a set of recommended responses to the first message, the set of recommended responses being a subset of the set of candidate responses; and causing the set of recommended responses to be presented by a client device of a recipient user of the first message. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A messaging system comprising:
-
one or more computer processors; and one or more computer-readable mediums storing instructions that, when executed by the one or more computer processors, cause the messaging system to perform operations comprising; receiving a first message being transmitted as part of communication session, the first message including a plurality of sequenced words; generating, using a sequence to sequence encoder included in a sequence to sequence to classification model, a first embedding vector representing the plurality of sequenced words included in the first message the sequence to sequence to classification model including the sequence to sequence encoder and a text classification model, the sequence encoder having been trained based on historical message data that includes messages transmitted between users of the messaging system and the text classification model having been trained based on embedding vectors generated by the sequence to sequence encoder from the historical message data; generating a feature vector based on the first embedding vector and at least a first feature that is not included in the first embedding vector; generating a set of candidate responses for replying to the first message by using the feature vector as input into the text classification model, the set of candidate responses being a subset of a set of available responses; selecting, from the set of candidate responses, a set of recommended responses to the first message, the set of recommended responses being a subset of the set of candidate responses; and causing the set of recommended responses to be presented by a client device of a recipient user of the first message. - View Dependent Claims (8, 9, 10, 11, 12)
-
-
13. A non-transitory computer-readable medium storing instructions that, when executed by one or more computer processors of a messaging system, cause the messaging system to perform operations comprising:
-
receiving a first message being transmitted as part of communication session, the first message including a plurality of sequenced words; generating, using a sequence to sequence encoder included in a sequence to sequence to classification model, a first embedding vector representing the plurality of sequenced words included in the first message the sequence to sequence to classification model including the sequence to sequence encoder and a text classification model, the sequence encoder having been trained based on historical message data that includes messages transmitted between users of the messaging system and the text classification model having been trained based on embedding vectors generated by the sequence to sequence encoder from the historical message data; generating a feature vector based on the first embedding vector and at least a first feature that is not included in the first embedding vector; generating a set of candidate responses for replying to the first message by using the feature vector as input into the text classification model, the set of candidate responses being a subset of a set of available responses; selecting, from the set of candidate responses, a set of recommended responses to the first message, the set of recommended responses being a subset of the set of candidate responses; and causing the set of recommended responses to be presented by a client device of a recipient user of the first message. - View Dependent Claims (14, 15, 16, 17, 18)
-
Specification