Microsoft Technology Licensing, LLC

Other

Craig Martell

Vita G Markman

Yongzheng Zhang

Lutz Thomas Finger

Frederick S M Herz

Sanjay Kshetramade

Muhieddine El Kaissi

Yael Gertner

Mohammad Shafkat Amin

Alexander Chiocchi

Majid Yazdani

Sampath Kannan

Xiao Bao

Daniel ManHung Wong

Anmol Bhasin

Dan Shacham

Uri Merhav

Baoshi Yan

Vitaly Gordon

Fan Yang

Kin Fai Kan

Lifeng Sang

Ganesan Venkatasubramanian

Maulin Patel

Shivakumar Edayathumangalam Raman

Siddharth Agarwal

Vicente Barbosa Da Silveira

Arpit Amar Goel

A method is provided. The method comprises receiving, from a user device, a current search query that is in an unstructured format; after receiving the current search query from the user device, retrieving a corresponding current list of facets with a current list of associated values and a context of the current search query, the context comprising a previous search query from the user device and a corresponding previous list of facets with a previous list of associated values; determining a group of actions on one or more of the current list of facets with the current list of associated values and the previous list of facets with the previous list of associated values based on the current search query; creating an updated list of facets with an updated list of associated values based on the group of actions; generating a database query based on the updated list of facets with the updated list of associated values; causing a database search with the database query; transmitting a search result of the database search to the user device, wherein the method is performed by one or more computing devices.

Facet-based conversational search

A method is provided. The method comprises receiving a search query that is part of a search conversation, the search query in an unstructured format; identifying a first list of facets with a first list of associated values from the search query; deriving a second list of facets with a second list of associated values from the first list of facets based on a context of the search query within the search conversation; generating a database query based on the second list of facets with the second list of associated values; causing a database search with the database query; transmitting a search result of the database search to a sender of the search query, wherein the method is performed by one or more computing devices.

Hybrid classification system and method are described. The method commences when an input detector detects a raw input string that represents a value of a category in a member profile maintained by the on-line social network. The machine learning classifier derives a standardized value corresponding to the raw input string. The trigger module provides the raw input string to the correcting filter. The correcting filter determines a corrected standardized value corresponding to the raw input string based on the raw input string and a corrective rule. The label module then identifies the member profile as associate with the corrected standardized value.

Hybrid classification system

The disclosed embodiments provide a system for processing data. During operation, the system obtains a set of topics associated with a set of content items. Next, the system obtains a first set of attributes associated with a first topic in the set of topics and a second set of attributes associated with a second topic in the set of topics. Next, the system calculates a similarity between the first and second sets of attributes and applies a threshold to the similarity to identify the first and second topics as synonymous when the similarity exceeds a threshold. The system then merges the first and second topics under a representative topic. Finally, the system displays the representative topic to a user to improve understanding of the set of content items by the user without requiring the user to manually analyze the set of content items.

Detecting and combining synonymous topics

This disclosure relates to systems and methods that include receiving media content from a content submitter, classifying the media content by initiating one of synchronous classification and asynchronous classification based on a type of the media content, generating a media content certificate based on the media type, the certificate including results of the classification, storing the media content certificate with the media content, and filtering the media content based on at least one of an identity of the content submitter, the results of the classification, and the media content including malicious content.

Managing distribution of media content

The disclosed embodiments provide a system for processing data. During operation, the system obtains a set of clauses in a first set of content items comprising unstructured data. Next, the system obtains a set of stop words comprising high-frequency words that occur in a second set of content items. The system then automatically extracts a set of topics from the set of clauses by generating a set of n-grams from the set of clauses and excluding a first n-gram in the set of n-grams from the set of topics when the first n-gram contains a word in the set of stop words in a pre-specified position of the first n-gram. Finally, the system displays the set of topics to a user to improve understanding of the first set of content items by the user without requiring the user to manually analyze the first set of content items.

Topic extraction using clause segmentation and high-frequency words

This disclosure provides systems and methods for determining a classification model for a secondary language different from a primary language. A social networking server is configured to obtain primary language content written in a first spoken language and secondary language content written in a second spoken language. The social networking server further obtains a machine translation of the primary language content. The social networking server then determines an initial language model from the machine translation. The social networking further determines a language model perturbation using the initial language model, where the language model perturbation accounts for a difference between the machine translation and the secondary language content. The social networking server also determines a classification model from the initial language model and the language model perturbation, which is then applied to a plurality of comments associated with an item of interest provided by a social networking service.

Transfer learning for bilingual content classification

The disclosed embodiments provide a system for processing data. During operation, the system obtains a set of content items and a set of topics in the set of content items. For each topic in the set of topics, the system automatically extracts a set of attributes that provides a context for the topic from a subset of the content items containing the topic. The system then displays the set of attributes in the context of the topic to improve understanding of the set of content items by the user without requiring the user to manually analyze the set of content items.

Attribute-based contexts for sentiment-topic pairs

A title standardization system is may be configured to detect an edit operation associated with the job title field of a member profile stored by an on-line social network system and, in response, perform operations to derive a canonical title that represents a raw title string found in the job title field. The derived canonical title may be then associated with the member profile, in which the originally-obtained subject title string was found. This association may be stored in a database for future use, e.g., for targeting job recommendations, recruiting, making professional contacts, as well as for other purposes.

Title standardization

An encryption scheme that uses steganography includes an encryption algorithm that encrypts messages by embedding them in a data stream in such a way that an adversary cannot get information about the messages. Since the embedding is the only computation required, this scheme is optimal in computational efficiency. However, since the size of the data stream is large, this scheme is most beneficial when the cost of bandwidth is less expensive than the cost of computation. The scheme embeds the message as specified by a pseudo random generator.

System and method for encrypting data in pictorial data

We propose a multi user information theoretically secure scheme. Our scheme allows any two parties in a multi user system to exchange messages securely using encryption, and to sign messages. Our scheme achieves a significant saving in the number of total keys in the system and in the keys each user must store. The encryption, and signing algorithms proposed in the scheme are as efficient as possible. Our scheme is designed so that it is possible to easily and efficiently revoke and add membership of new users into the system. It is also designed so that authentication and security against man in the middle attacks can be added at low cost. In addition, we introduce a novel and efficient way to use steganography for key replenishment.

Growing community of inventors

San Juan Bautista, CA, United States of America

Craig Martell