Abstract: Techniques for enhanced table and text question answering based on multi-instance, multi-answer training are presented. An answer extractor component can determine answer scores associated with candidate answer data items based on analysis of a set of data, comprising row data items of a table and passage data items associated with the table, and a context of a query of the set of data. The answer extractor component can be trained based on application of denoised single-instance and multiple-instance answer matching data associated with contexts to an answer extractor model to generate a trained answer extractor model of the answer extractor component. A query response component can determine a correct answer data item responsive to the query from the candidate answer data items based on the answer scores associated with the candidate answer data items, wherein the candidate answer data items can be reranked based on reweighted answer scores.

Abstract: A question answering bot that digests non-relational data tables is provided. A processor receives a question regarding a non-relational data table. A processor extracts at least one feature of the question using a natural language processing (NLP) model. A processor extracts at least one similar feature of the non-relational data table to the extracted at least one feature of the question. A processor determines at least one relevant cell in the non-relational data table based on the at least one feature of the question and the at least one similar feature of the non-relational data table. A processor provides an answer to the question, where the answer is based on the at least one relevant cell.

Abstract: One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to building a unified question generation system across languages and modalities. The computer-implemented system can comprise a memory that can store computer executable components. The computer-implemented system can further comprise a processor that can execute the computer executable components stored in the memory, wherein the computer executable components can comprise a training component that can train a unified question generation model to generate questions in a language from a first modality in the language using training data comprising one or more second modalities in the language different from the first modality, wherein the first modality and the one or more second modalities can include at least one of one or more tables, one or more passages, or a combination of the one or more tables and the one or more passages.

Abstract: Retrieval aware natural language question generation for open domain document retrieval is provided. In one aspect, a system for retrieval aware question generation includes: a question decontextualizer configured to decontextualize a question generated from a context of a target document by adding terms from the context into the question itself to create a decontextualized question, where the decontextualized question alone enables open domain document retrieval without a need for also providing the context. The system can also include a detect document identifier configured to find the terms in the context; and a retriever configured to retrieve documents from the corpus of documents using the decontextualized question. A method for retrieval aware question generation using the present system is also provided.

Abstract: One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to a process to facilitate a Question Generation System. A system can comprise a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components can comprise a receiving component that receives a corpus of documents that contain Tables (Ts) and Passages (Ps) for performing natural language processing (NLP); an executing component that executes the NLP by employing the tables (sT) and passages (Ps) as primary inputs; and a query component that generates an output Question (Q) based on a subset of the tables Ts and passages (Ps).

Abstract: Methods, systems, and computer program products for providing a contextual dialogue framework over dynamic tables are provided herein. A computer-implemented method includes maintaining a context space for a natural language conversation of a user, wherein the context space comprises a dynamic set of one or more tables used for processing at least one query of the natural language conversation; obtaining an additional table associated with an additional query of the natural language conversation; discovering one or more implicit links between the additional table and the dynamic set of tables; updating the context space with the one or more implicit links; and answering the additional query based at least in part on the updated context space.

Abstract: Techniques for enhanced table and text question answering based on multi-instance, multi-answer training are presented. An answer extractor component can determine answer scores associated with candidate answer data items based on analysis of a set of data, comprising row data items of a table and passage data items associated with the table, and a context of a query of the set of data. The answer extractor component can be trained based on application of denoised single-instance and multiple-instance answer matching data associated with contexts to an answer extractor model to generate a trained answer extractor model of the answer extractor component. A query response component can determine a correct answer data item responsive to the query from the candidate answer data items based on the answer scores associated with the candidate answer data items, wherein the candidate answer data items can be reranked based on reweighted answer scores.

Abstract: A question answering bot that digests non-relational data tables is provided. A processor receives a question regarding a non-relational data table. A processor extracts at least one feature of the question using a natural language processing (NLP) model. A processor extracts at least one similar feature of the non-relational data table to the extracted at least one feature of the question. A processor determines at least one relevant cell in the non-relational data table based on the at least one feature of the question and the at least one similar feature of the non-relational data table. A processor provides an answer to the question, where the answer is based on the at least one relevant cell.

Abstract: Methods, systems, and computer program products for automated code-mixed natural language processing for artificial intelligence-based question answering techniques are provided herein. A computer-implemented method includes detecting multiple languages in an input query to an artificial intelligence-based question answering system; determining, in the input query, one or more partial query signals associated with each of the multiple languages; identifying one or more missing entity arguments from at least a portion of the one or more partial query signals; updating at least a portion of the one or more missing entity arguments by inferring data from at least a portion of the one or more partial query signals using at least one artificial intelligence technique; and performing one or more automated actions based at least in part on the updating of at least a portion of the one or more missing entity arguments.

Abstract: Methods, systems, and computer program products for automated few-shot learning techniques for artificial intelligence-based query answering systems are provided herein. A computer-implemented method includes obtaining multiple sets of queries and answers associated with one or more tables; determining a level of complexity attributed to at least a portion of the queries from the multiple sets of queries and answers; determining, based at least in part on the determined level of complexity attributed to the at least a portion of the queries, one or more new queries for use in training at least one artificial intelligence-based query answering system; facilitating annotation of the one or more new queries; training the at least one artificial intelligence-based query answering system using at least a portion of the one or more annotated new queries; and performing at least one automated action using the at least one trained artificial intelligence-based query answering system.

Abstract: Methods, systems, and computer program products for providing a contextual dialogue framework over dynamic tables are provided herein. A computer-implemented method includes maintaining a context space for a natural language conversation of a user, wherein the context space comprises a dynamic set of one or more tables used for processing at least one query of the natural language conversation; obtaining an additional table associated with an additional query of the natural language conversation; discovering one or more implicit links between the additional table and the dynamic set of tables; updating the context space with the one or more implicit links; and answering the additional query based at least in part on the updated context space.

Abstract: Methods, systems, and computer program products for automatically generating factsheets for artificial intelligence-based question answering systems are provided herein.

Abstract: Methods, systems, and computer program products for self-supervision in table question answering are provided herein. A computer-implemented method includes obtaining a table comprising a plurality of entries, wherein each entry corresponds to a particular column and particular row of the table; identifying one or more of the entries in the table that correspond to a target answer of a natural language query; generating an intermediate representation of the table comprising the rows corresponding to the identified one or more entries, wherein the intermediate representation masks each of the identified one or more entries; and generating a set of natural language question and answer pairs based on the intermediate representation.