Various embodiments provide methods, apparatus, systems, computing entities, and/or the like, for providing a summarization of a conversation, such as a telephonic conversation. In an embodiment, a method is provided. The method comprises receiving an input data object comprising textual data of a conversation, the textual data comprising sentence-level tokens. The method further comprises classifying some sentence-level tokens as interrogative sentence-level tokens, and identifying subtopic portions of the textual data, each interrogative sentence-level token located within one subtopic portion. The method further comprises determining whether an interrogative sentence-level token is substantially similar to one of a plurality of target queries, and for such interrogative sentence-level tokens, selecting sentence-level tokens from a subtopic portion corresponding to the such interrogative sentence-level tokens. The method then comprises generating a summarization data object comprising the selected sentence-level tokens for each interrogative sentence-level token substantially similar to a target query and performing summarization-based actions.

This disclosure relates to a search result processing method and apparatus, and a storage medium. The method may include acquiring a search result according to a search keyword and obtaining an accurate matching score of the search result relative to the search keyword. The method may further include determining a semantic matching weight vector of the search result, a semantic representation vector of the search keyword, and a semantic representation vector of the search result. The method may further include obtaining a semantic matching score of the search result relative to the search keyword according to the semantic representation vectors and the semantic matching weight vector. The method may further include obtaining a similarity between the search result and the search keyword according to the accurate matching score and the semantic matching score.

An electronic apparatus and a controlling method thereof are provided. The electronic apparatus includes a memory configured to store at least one instruction, and a processor configured to execute the at least one instruction to control the electronic apparatus to: determine a keyword from a query based on the query being input, obtain a word related to the keyword based on information on a user preference, and provide a response to the user query based on the keyword and the word. The processor may be configured to control the electronic apparatus to obtain at least one word from among a plurality of candidate words corresponding to the keyword as a word related to the keyword based on the user preference information. For example, at least part of a method of providing a response to a query by the electronic apparatus may use an AI model that is trained using at least one of machine learning, neural network or deep learning algorithm.

A method, apparatus and computer program product, the method comprising: obtaining a graph having a multiple nodes and one or more edges, each node comprising a set of entities having a common property and a subject, and each edge connecting two nodes and indicating a relationship therebetween; obtaining a query from a user, wherein the search query comprises a free-form text; extracting from the free-form one or more keyword combinations and one or more logic terms; for each keyword combination, creating a list of nodes from the graph based on a relevancy of the subject of each of the nodes with respect to the keyword combination; creating a collection of entities comprised in the list of nodes, said creating comprises filtering out entities associated with a node that is excluded based on the logic term; and providing a response to the query, wherein the response comprises the collection of entities.

Systems and methods of processing a query from a user. A method includes receiving, by a server computer, an initial question from a client computer. The initial question includes a plurality of words and the server computer can identify a set of words in the plurality of words. Then the server computer can determine a list of clarifying questions based on a subset of the set of words. The server computer presents the list of clarifying questions to the client computer and receiving clarifying answers to the clarifying questions. The server computer determines an answer to the initial question and presents the answer to the client computer.

This invention presents a framework for applying artificial intelligence to aid with product design, mission or retail planning. The invention outlines a novel approach for applying predictive analytics to the training of a system model for product design, assimilates the definition of meta-data for design containers to that of labels for books in a library, and represents customers, requirements, components and assemblies in the form of database objects with relational dependence. Design information can be harvested, for the purpose of improving decision fidelity for new designs, by providing such database representation of the design content. Further, a retrieval model, that operates on the archived design containers, and yields results that are likely to satisfy user queries, is presented. This model, which is based on latent semantic analysis, predicts the degree of relevance between accessible design information and a query, and presents the most relevant previous design information to the user.

Approaches for multitask learning as question answering include a method for training that includes receiving a plurality of training samples including training samples from a plurality of task types, presenting the training samples to a neural model to generate an answer, determining an error between the generated answer and the natural language ground truth answer for each training sample presented, and adjusting parameters of the neural model based on the error. Each of the training samples includes a natural language context, question, and ground truth answer. An order in which the training samples are presented to the neural model includes initially selecting the training samples according to a first training strategy and switching to selecting the training samples according to a second training strategy. In some embodiments the first training strategy is a sequential training strategy and the second training strategy is a joint training strategy.

Systems, computer-implemented methods, and computer program products to facilitate query recommendation are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an ontology component that can generate an ontology based on unstructured data of a description of an application programming interface. The computer executable components can further comprise a reasoner component that can identify one or more terms of the ontology that correspond semantically to a term of a query.

A method of operating a messaging platform, including: obtaining, for a first profile, a first and a second topic of interest, a first intra-profile (IP) weight for the first topic of interest, and a second IP weight for the second topic of interest; obtaining a first plurality of trending entities for the first topic and a first plurality of intra-topic (IT) weights for the first plurality of trending entities; obtaining a second plurality of trending entities for the second topic and a second plurality of IT weights for the second plurality of trending entities; selecting a subset of the first plurality of trending entities and the second plurality of trending entities based on the first IP weight, the second IP weight, the first plurality of IT weights, and the second plurality of IT weights; and sending content associated with the subset for display to a user of the first profile.

Systems and methods for extracting data from unstructured data sources based on proximity co-reference resolution model. The method includes receiving an electronic document from an unstructured data source and extracting entities from the electronic document. The method also includes receiving fields to be extracted from the electronic document and generating keywords based on the fields. Each of the entities is associated with at least one of the fields. The method further includes identifying keywords in the electronic document based on the generated keywords and calculating, for each of the fields, proximity scores based on a proximity co-reference resolution model. The method also includes, for each of the fields, identifying a field-entity pair based on the calculated proximity scores and generating for display on a user device the field-entity pair.