Microsoft Technology Licensing, LLC

Yan Gao

Dongmei Zhang

Ajith Muralidharan

Jian-Guang Lou

Sandor Nyako

Shaunak Chatterjee

Jinyun Yan

Maria Del Mar Gines Marin

Pratik Daga

Changji Shi

Nirav Nalinbhai Shingala

Matthew Walker

Zhongen Tao

Bei Chen

Yan Xiao

Bethany J Wang

Lei Fang

According to implementations of the subject matter described herein, a solution for semantic parsing of the natural language query is provided. In this solution, a first natural language query for a first data table is received, where the first natural language query comprises words. A first set of knowledge representations associated with the first data table are obtained and the first set of knowledge representations describe, in a structured manner, knowledge required for understanding a natural language query for the first data table. The first natural language query is converted into a first sequence of symbols. A first computer-executable query corresponding to the first natural language query is generated. According to this solution, various kinds of knowledge representations from different fields can be represented into universal structured knowledge representations, such that the knowledge representations are used to assist in understanding semantics of natural language queries and generating corresponding computer-executable queries.

Semantic parsing of natural language query

In accordance with implementations of the present disclosure, a solution for converting a natural language query is provided. In this solution, a first natural language query and a second natural language query for one or more data tables are received, wherein semantics of the second natural language query is dependent on the first natural language query. A third natural language query for one or more data tables is generated based on the first natural language query and the second natural language query, wherein semantics of the third natural language query is identical to the semantics of the second natural language query and independent of the first natural language query. In this way, this solution can convert a context-dependent natural language query into a context-independent natural language query, thereby enabling interfacing with any semantic parsers which can convert a natural language query into a computer-executable query.

Conversion of natural language query

Technologies for generating dynamic notification content for notification messages using a machine learned model are provided. The disclosed techniques include identifying an event related to a particular user, where the event has a particular notification type that represents a subject type of the event. Based on the particular notification type of the event, a set of candidate headline and call-to-action combinations corresponding to the particular notification type are identified. Using the machine learned model, scores are calculated for each headline and call-to-action combination in the set of candidate headline and call-to-action combinations. One or more particular headline and call-to-action combinations from the set of candidate headline and call-to-action combinations are selected based upon the scores calculated for each combination of the set of candidate headline and call-to-action combinations. A notification message is generated for the event that includes the one or more particular headline and call-to-action combinations selected.

Machine learning driven dynamic notification content

Techniques for identifying and delivering notifications of user-generated content to network-limited users are provided. In one technique, for each selected target entity that has a limited network, one or more topics associated with the target entity are identified and the target entity is assigned to one or more entity-topic buckets for the identified topics. For each selected content item, one or more topics associated with the content item are identified and the content item is assigned to one or more content-topic buckets for the identified topics. The entity-topic buckets are matched to the content-topic buckets, resulting in assigning, for each selected target entity, zero or more content items to that target entity. For each target entity that is assigned one or more content items based on the matching, a notification is generated and transmitted over a computer network to a computing device of the target entity.

Out-of-network notifications of network-transmitted content items

A notification platform for distribution of notification content in an on-line social network system addresses the technical problem of optimizing the volume of quality notifications that are being delivered to a given member. A notification delivery system is designed as a stream processing system that can fetch, store, and process data in a near-line fashion. It can perform feature generation, processing and scoring of notifications, as well as ranking of the notifications based on their respective relevance scores that are calculated using machine learning techniques. The notification delivery system is positioned centrally with respect to different producers of notifications, such that it can consume centrally-stored information about members' holistic notification experiences.

Near real time relevance ranker for notifications

Growing community of inventors

Los Altos, CA, United States of America

Yan Gao