At least some embodiments are directed to a system to compute uniform structured summarization of customer chats. In at least some embodiments, the system may operate a processor and receive a corpus of chats between customers and customer service representatives of an enterprise. Grouping the corpus of chats into subgroup task types and then extracting chat keywords and chat related words for each subgroup task type. Generating an expandable template data structures for each subgroup task type. Processing at least one chat to extract chat utterances and chat snippets ranking the chat utterances and chat snippets. Populating the expandable template data structure based on rankings to generate a chat summary data structure.

Methods and systems are provided for discriminating ambiguous expressions to enhance user experience. For example, a natural language expression may be received by a speech recognition component. The natural language expression may include at least one of words, terms, and phrases of text. A dialog hypothesis set from the natural language expression may be created by using contextual information. In some cases, the dialog hypothesis set has at least two dialog hypotheses. A plurality of dialog responses may be generated for the dialog hypothesis set. The dialog hypothesis set may be ranked based on an analysis of the plurality of the dialog responses. An action may be performed based on ranking the dialog hypothesis set.

A patent claims disassembling and analyzing device which automatically retrieves a patent claims and performs the following modules: a claim dependency determining module, a patent-claims-separating module, a preamble retrieving module, an independent-claim-element-analyzing module, and a dependent-claim-element-analyzing module, thereby disassembling and analyzing a patent claims of a patent.

Dependency trees are generated for questions and answers of a question answering (QA) corpus in which the answers are associated with the questions. Generating the dependency trees includes identifying root nodes. A word near an identified root node of one of the questions is compared to words of answers associated with the one of the questions. The word is determined to be in less than a threshold number of the associated answers. The word is identified as a stop word.

In one example in accordance with the present disclosure, a method may include separating a list of keywords into a set of word tokens and a set of wildcard tokens. The method may also include removing each wildcard token in the set of wildcard tokens that is inferred by at least one word token in the set of word tokens and removing each wildcard token in the set of wildcard tokens that is inferred by at least one other wildcard token in the set of wildcard tokens. The method may also include executing a search query comprising a new list of keywords that includes each wildcard token not removed from the set of wildcard tokens.

Provided is a method and system for normalizing catalog item data to create higher quality search results. In one example, the method may include receiving a record comprising an unstructured description of an object, identifying a type of the object from among a plurality of object types and identifying a predefined attribute of the identified type of object, extracting a value from the unstructured description corresponding to the predefined attribute and modifying the extracted value to generate a normalized attribute value, and storing a structured record of the object in a structured format comprising a plurality of values of a plurality of attributes of the object from the unstructured description including the normalized attribute value for the predefined attribute of the object.

An analytics platform for the extraction of structured observations from largely narrative sources using a hybrid approach of user configuration and machine learning is provided. The analytics platform collects and normalizes data from public and private sources and applies extractions to the data to create a world view of objects, traits, and relationships of interest and maintains that world view as data and/or extractions are updated. The platform is further configured to apply queries to the extracted world view for a variety of purposes including scoring objects for prioritized attention, generating notifications when specific conditions are met, providing data sets for exploratory analysis, and triggering the automatic collection of enhancing data from external sources.

A confidentiality preserving system and method for performing a rank-ordered search and retrieval of contents of a data collection. The system includes at least one computer system including a search and retrieval algorithm using term frequency and/or similar features for rank-ordering selective contents of the data collection, and enabling secure retrieval of the selective contents based on the rank-order. The search and retrieval algorithm includes a baseline algorithm, a partially server oriented algorithm, and/or a fully server oriented algorithm. The partially and/or fully server oriented algorithms use homomorphic and/or order preserving encryption for enabling search capability from a user other than an owner of the contents of the data collection. The confidentiality preserving method includes using term frequency for rank-ordering selective contents of the data collection, and retrieving the selective contents based on the rank-order.

Disclosed is a system for rectifying a typographical error in a text file. The system includes a network generating module for generating a linguistic network of a plurality of words present in the text file. A computation module configured to compute the similarity between each pair of words based on a set of parameters. A weight assignment module for assigning a weight to the edge present between the each pair of words based the set of parameters. A categorization module configured to categorize one or more words present in the linguistic network in a category. A word identification module configured to identify a reference word from the category. A word substitution module configured to substitute each word of the category deemed as erroneous with corresponding reference word for rectifying the typographical error.

An intelligent assistant device for conversation-based indexing and searching of a file. The intelligent assistant device having a processor configured to detect a conversation having at least one user. The processor, responsive to detecting the conversation having at least one user configured to mine the conversation for a file associated with the conversation. The processor, responsive to identifying the file further configured to mine the conversation for contextual keywords associated with the file. The processor also configured to index the contextual keywords to the file.