Abstract: This disclosure relates generally to long-form answer extraction and, more particularly, to long-form answer extraction based on combination of sentence index generation techniques. Existing answer extractions techniques have achieved significant progress for extractive short answers; however, less progress has been made for long form questions that require explanations. Further the state-of-art long-answer extractions techniques result in poorer long-form answers or not address sparsity which becomes an issue longer contexts. Additionally, pre-trained generative sequence-to-sequence models are gaining popularity for factoid answer extraction tasks. Hence the disclosure proposes a long-form answer extraction based on several steps including training a set of generative sequence-to-sequence models comprising a sentence indices generation model and a sentence index spans generation.

Abstract: Conventional Question and Answer (QA) datasets are created for generating factoid questions only and the present disclosure generates longform technical QA dataset from textbooks. Initially, the system receives a technical textbook document and extracts a plurality of contexts. Further, a first plurality of questions are generated based on the plurality of contexts. A plurality of answerable questions are generated further based on the plurality of contexts using an unsupervised template-based matching technique. Further, a combined plurality of questions are generated by combining the first plurality of questions and the plurality of answerable questions. Further, an answer for the combined plurality of questions are generated using an autoregressive language model and a mapping score is computed. Further, a plurality of optimal answers are selected based on the corresponding mapping score.

Abstract: Technical interviewing is important for organizations for assessing a candidate to make hiring decision. For effective technical interviewing, predicting difficulty of long form technical questions is crucial. The present disclosure provides systems and methods for predicting difficulty of long form technical questions using weak supervision from textbooks. Further, zero shot pre-trained large language models and unsupervised template-based technique are used for generating questions. Furthermore, a difficulty score is assigned to the generated questions based on context difficulty and task difficulty. The context difficulty for the generated questions is computed using hierarchical structure of the textbooks, and the task difficulty is computed by determining a similarity between the generated questions and Bloom's taxonomy levels.

Abstract: The present disclosure a method for document structure based unsupervised long-form technical question generation. Initially, the system receives a textbook document. Further, a PDF metadata is extracted from the textbook document using a Natural Language Processing (NLP) technique. Further, a plurality of structures from the textbook document based on the PDF metadata using an NLP based filtering technique. Further, a plurality of index based question templates and Table of Contents (TOC) based question templates are obtained from a plurality of predefined question templates using the plurality of structures. Further, the generated plurality of long-form technical questions are generated using the obtained index and TOC based question templates. The plurality of long-form technical questions are further evaluated by the system using plurality of metrics.

Abstract: Functionality from a line of business application can be exposed as a web service. User input is received that requests information about objects exposed by a line of business application. Metadata is also gathered about a first set of objects exposed by the line of business application. The metadata is returned to the user. User input is received selecting a second set of objects from among the first set of objects to be exposed as a web service. A web service model is constructed that exposes the second set of objects. The web service model includes a service description, metadata map, and configuration information. The web service model is published to allow for web service clients to access the second set of objects by accessing the web service model. The web service can then be used to translate messages between a line of business application and one or more web service clients.

Abstract: Functionality from a line of business application can be exposed as a web service. User input is received that requests information about objects exposed by a line of business application. Metadata is also gathered about a first set of objects exposed by the line of business application. The metadata is returned to the user. User input is received selecting a second set of objects from among the first set of objects to be exposed as a web service. A web service model is constructed that exposes the second set of objects. The web service model includes a service description, metadata map, and configuration information. The web service model is published to allow for web service clients to access the second set of objects by accessing the web service model. The web service can then be used to translate messages between a line of business application and one or more web service clients.

Abstract: Exposing functionality from a line of business application as a web service. A method includes receiving user input requesting information about objects exposed by a line of business application. Metadata is gathered about a first set of objects exposed by the line of business application. The metadata is returned to the user. User input is received selecting a second set of objects from among the first set of objects to be exposed as a web service. A web service model is constructed that exposes the second set of objects. The web service model includes a service description, metadata map, and configuration information. The web service model is published to allow for web service clients to access the second set of objects by accessing the web service model. The web service can then be used to translate messages between a line of business application and one or more web service clients.

Abstract: Detailed herein is a technology which, among other things, allows a search engine to utilize a user-defined relevance function. In one approach to the technology, a method of applying a user-defined relevance function is described. In this approach, a complex search query is decomposed into a simple operator. The simple operator is associated with the user-defined relevance function. A document which matches the search query is retrieved, and a rank is calculated for the document, using the user-defined relevance function.

Abstract: Exposing functionality from a line of business application as a web service. A method includes receiving user input requesting information about objects exposed by a line of business application. Metadata is gathered about a first set of objects exposed by the line of business application. The metadata is returned to the user. User input is received selecting a second set of objects from among the first set of objects to be exposed as a web service. A web service model is constructed that exposes the second set of objects. The web service model includes a service description, metadata map, and configuration information. The web service model is published to allow for web service clients to access the second set of objects by accessing the web service model. The web service can then be used to translate messages between a line of business application and one or more web service clients.

Abstract: Facilitating communication from web service clients to line of business applications. A method includes method obtaining a connection from a connection pool. The connection pool pools line of business connections available for accessing a line of business application. The method further includes using the connection, transferring messages between a web service client and the line of business application.

Abstract: Detailed herein is a technology which, among other things, allows a search engine to utilize a user-defined relevance function. In one approach to the technology, a method of applying a user-defined relevance function is described. In this approach, a complex search query is decomposed into a simple operator. The simple operator is associated with the user-defined relevance function. A document which matches the search query is retrieved, and a rank is calculated for the document, using the user-defined relevance function.

Abstract: The subject invention pertains to database reverse query matching. A text document can be received and analyzed to determine which, if any, queries the document matches. To enable such functionality, a number of intermediate structures such as tables are generated in accordance with designated queries. In particular, a canonical table can be generated that specifies the expressions or phrases as well as match rules. Furthermore, a Boolean table can be generated that specifies the Boolean relationship of expressions in canonical table. A match component or methodology can match text phrases to query phrases identified by the canonical table. An evaluation component or related methodology can subsequently utilize the Boolean table to determine if the preliminary phrase matches match the query logic.

Abstract: A full-text search index system and method is generated by creating instances of a database index from an in-memory inverted list of keywords associated with a text identifier and the occurrences of the keyword in the text. Instances of the index are placed in a priority queue. A merge scheduling process determines when a merge should be initiated, selects instances of the index to be merged and selects a type of merge to perform. Instances of an index are assigned a temporal indicator (timestamp). A set of instances is selected to be merged. The set of instances is validated and merged.

Abstract: A full-text search index system and method is generated by creating instances of a database index from an in-memory inverted list of keywords associated with a text identifier and the occurrences of the keyword in the text. Instances of the index are placed in a priority queue. A merge scheduling process determines when a merge should be initiated, selects instances of the index to be merged and selects a type of merge to perform. Instances of an index are assigned a temporal indicator (timestamp). A set of instances is selected to be merged. The set of instances is validated and merged.

Abstract: The present invention relates to an integrated full-text search architecture that integrates full text search with database server applications in a tight manner so that it becomes part of the server in all aspects including storage, metadata, query processing, back/up restore and resource management. This provides improved performance with respect to queries as well as improved manageability. Furthermore, the subject architecture is open and schema directed unlike other conventional full-text search architectures. Accordingly, the full-text search architecture enables expert users (e.g., search providers) to define their own index structures as well as ranking algorithms.