Linkedin Corporation

Microsoft Technology Licensing, LLC

Servicenow, Inc.

Wal-mart Stores, Inc.

Rupert Labs, Inc.

Mitul Tiwari

Curtis Wang

Samir Mavji Shah

Roshan Rajesh Sumbaly

Quaizar Vohra

Madhusudan Mathihalli

Ravi Narasimhan Raj

Deepak Bobbarjung

Srivatsava Daruru

Kaushik Rangadurai

Abhisaar Yadav

Myunghwan Kim

Shaunak Chatterjee

Yu Shi

Abhishek Gattani

Anand Rajaraman

Srinivas Vemuri

Aastha Jain

Anil Kumar Madamala

Sri Subramaniam

Mehul Shah

Maneesh Varshney

Souvik Ghosh

Romer E Rosales-Delmoral

June H Andrews

Brad Christopher Ciraulo

Haifeng Ji

Vinitha Reddy Gankidi

Jignesh Parmar

Olivier Nguyen

Xin Cai

Ajit Datar

Andrew P Hill

Soham Parikh

Kurt MacDonald

Ziaul Hasan Hashmi

Orlando Marquez

Patrice Bechard

Shounak Purkayastha

Wenlei Xie

Suvodeep Pyne

Shruti Bhosale

A method is provided for efficiently providing sentiments or other manual labels for textual training data. The method includes using an embedding model to project acquired user text to an embedding vector in an embedding space. Distances (e.g., cosine similarities) between this embedding vector and the embedding vectors determined for a plurality of already-label user text training examples are then determined. The already-labeled user text that has the shortest distance is determined and the label thereof is prospectively applied to the acquired user text and presented to a user for approval. The user can approve the prospectively applied label, in which case the newly acquired text is added to the training data with the prospectively applied label associated therewith for later use in training a language model. Alternatively, the user can decline the prospectively applied label and apply an alternative label to the newly acquired text.

Method for filtering and semi-automatically labeling training data

Example data processing systems and methods are described. In one implementation, a system accesses a corpus of data and analyzes the data contained in the corpus of data to identify multiple documents. The system generates vector indexes for the multiple documents such that the vector indexes allow a computing system to quickly access the plurality of documents and identify an answer to a question associated with the corpus of data.

Generation and utilization of vector indexes for data processing systems and methods

Data processing systems and methods

Example systems and methods related to chatbot skills are described. In one implementation, a system initiates a session to create a new chatbot. The system receives a selection of a first chatbot skill associated with the new chatbot and a selection of a second chatbot skill associated with the new chatbot, where the first chatbot skill is different from the second chatbot skill. The system creates the new chatbot by importing the first chatbot skill and the second chatbot skill into the new chatbot.

Chatbot skills systems and methods

This disclosure is directed to large-scale graph processing to determine second-degree connections for members of a social network. A social graph is duplicated into two graphs, where each of the two graphs are partitioned into various partitions. The partitions are each sorted according to a predetermined key selected from each of the graphs. The partitions are then assigned logical Work Units, where a first set of Work Units are determined from a first graph and second set of Work Units are determined from a second graph. The Work Units are determined to be asymmetrical such that the partitions of the first set of Work Units are assigned differently than the partitions of the second set of Work Units. One set of Work Units are loaded in-memory and another set of Work Units are streamed to a mapping module process, which determines the second-degree connections from the sets of Work Units.

Joins and aggregations on massive graphs using large-scale graph processing

The disclosed embodiments provide a system for facilitating interaction within a social network. During operation, the system obtains a set of attributes of a social network of a first member and a set of historic interactions in the social network. Next, the system analyzes the attributes and the historic interactions to predict an effect of a potential interaction between the first member and a second member of the social network on subsequent interactions in the social network. The system then uses the predicted effect to generate output for modulating the subsequent interactions in the social network.

Characterizing and managing social network interactions

Disclosed in some examples are methods, systems, and machine-readable mediums which provide a relevance engine for determining a relevance of an individual (either a non-member or another member) to another individual (either a non-member or another member). This relevance engine may use signals in the form of data that the social networking service may learn about the individuals to determine how relevant the individuals are to each other.

Techniques to facilitate recommendations for non-member connections

This disclosure relates to systems and methods for expanding a social network. A method includes retrieving contact lists from a plurality of devices, generating a list of associations between identifiers in a first communication channel and identifiers in a second communication channel, removing, from the list of associations, one or more associations that include identifiers that do not represent contacts that are not members of the online social networking service, and transmitting an invitation to join the online social networking service to the second identifiers on the second communication channel for associations that remain in the list of associations.

Expanding a social network

A system, method, and apparatus are provided for identifying an ideal or target network of a member of a professional network or social network, or one or more characteristics of such a network. Based on a type of the member, one or more attributes of a profile of the member, and/or one or more goals of the member, characteristics may be identified that support achievement of those goals or that promote more effective use of the professional network or social network by the member. By way of illustration, an ideal or target user network of a member seeking to improve her future job opportunities may include a minimum number of connections to members employed by different organizations, while an ideal or target user network of a member seeking a mentor may include a maximum number of connections to members holding senior positions within the member's industry or functional area.

Identifying an ideal user network

Disclosed in some examples are methods, systems, and machine-readable mediums which provide a relevance engine for determining a relevance of an individual (either a non-member or another member) to another individual (either a non-member or another member). This relevance engine may use signals in the form of data that the social networking service may learn about the individuals to determine how relevant the individuals are to each other. Example applications may include ordering of connection invitations in a social networking service.

Connection invitation ordering

A system and method for contextual connection recommendation includes obtaining, with a processor from a database, contextual data and social graph data related to a pair of members of a social network who are not currently connected on the social network. A connection base score between the pair of members is generated based on the social graph data. A recommendation modifier is generated based on the contextual data. A connection recommendation modified score is determined by applying the recommendation modifier to the base score. A connection recommendation is provided to at least one of the pair of members based, at least in part, on the connection recommendation modified score.

Contextual connection recommendation in a social network

Providing information to a module is disclosed. A first query and one or more subject type concepts associated with the first query is received. A second query to be provided to the module based at least in part on the received first query and subject type concepts is determined. The second query is sent to the module.

Providing information to modules

Growing community of inventors

Mountain View, CA, United States of America

Mitul Tiwari