Abstract: Methods, systems, and computer program products for natural language data generation using automated knowledge distillation techniques are provided herein. A computer-implemented method includes retrieving, in response to an input query, a set of passages from at least one knowledge base by processing the input query using a first set of artificial intelligence techniques; ranking at least a portion of the set of passages by processing the set of passages using a second set of artificial intelligence techniques; generating at least one natural language answer, in response to the input query, by processing a subset of the set of passages in connection with automated knowledge distillation techniques based on the ranking of the at least a portion of the set of passages; and performing automated actions based on the ranking of the at least a portion of the set of passages and/or the at least one generated natural language answer.

Abstract: Embodiments of the present invention provide a computer system, a computer program product, and a method that comprises analyzing a performed query by identifying a plurality of indicative markers based on a pre-stored classification database associated with the performed query; generating a plurality of facets based on the analysis of the performed query; selecting at least two facets within the generated plurality of facets by determining a quantitative similarity value between each respective facet and the plurality of identified indicative markers associated with the performed query; dynamically ranking the selected facets by prioritizing the selected facets based on a calculated overall score associated with assigned weighted values for each selected facet in the generated plurality of facets using a supervised machine learning algorithm; and displaying the dynamically ranked facets within a user interface of a computing device associated with a user.

Abstract: A first neural network is operated on a processor and a memory to encode a first natural language string into a first sentence encoding including a set of word encodings. Using a word-based attention mechanism with a context vector, a weight value for a word encoding within the first sentence encoding is adjusted to form an adjusted first sentence encoding. Using a sentence-based attention mechanism, a first relationship encoding corresponding to the adjusted first sentence encoding is determined. An absolute difference between the first relationship encoding and a second relationship encoding is computed. Using a multi-layer perceptron, a degree of analogical similarity between the first relationship encoding and a second relationship encoding is determined.

Abstract: Embodiments of the present invention provide computer-implemented methods, computer program products and computer systems. Embodiments of the present invention can, in response to receiving information, learn entity representations and cluster assignments of respective entity representations in a joint manner for both entities and relations of respective entities.

Abstract: A computer-implemented method for performing cross-document coreference for a corpus of input documents includes determining mentions by parsing the input documents. Each mention includes a first vector for spelling data and a second vector for context data. A hierarchical tree data structure is created by generating several leaf nodes corresponding to respective mentions. Further, for each node, a similarity score is computed based on the first and second vectors of each node. The hierarchical tree is populated iteratively until a root node is created. Each iteration includes merging two nodes that have the highest similarity scores and creating an entity node instead at a hierarchical level that is above the two nodes being merged. Further, each iteration includes computing the similarity score for the entity node. The nodes with the similarity scores above a predetermined value are entities for which coreference has been performed in input documents.

Abstract: Systems, devices, computer-implemented methods, and/or computer program products that facilitate generative relation linking for question answering over knowledge bases. In one example, a system can comprise a processor that executes computer executable components stored in memory. The computer executable components can comprise a relation linking component. The relation linking component can map relations identified in a natural language question to corresponding relations of a knowledge base using a generative model.

Abstract: One embodiment of the invention provides a method for terminology ranking for use in natural language processing. The method comprises receiving a list of terms extracted from a corpus, where the list comprises a ranking of the terms based on frequencies of the terms across the corpus. The method further comprises accessing a domain ontology associated with the corpus, and re-ranking the list based on the domain ontology. The resulting re-ranked list comprises a different ranking of the terms based on relevance of the terms using knowledge from the domain ontology. The method further comprises generating clusters of terms via a trained model adapted to the corpus, and boosting a rank of at least one term of the re-ranked list based on the clusters to increase a relevance of the at least one term using knowledge from the trained model.

Abstract: A computer-implemented method according to one embodiment includes converting an input question into a vector form using trained word embeddings; constructing a type similarity matrix using a predetermined ontology; and determining a score for all possible types for the input question, based on the input question in vector form and the type similarity matrix.

Abstract: A method, system, and computer program product for automated evaluation of information retrieval systems are provided. The method accesses a natural language query from a set of natural language queries. The natural language query is associated with a query difficulty level. The method generates one or more natural language responses to the natural language natural language query. Each natural language response is associated with at least one facet of the plurality of facets. The method generates a set of feedback cues. A set of search results for the natural language query are returned. The set of search results include a highest ranked natural language response of the one or more natural language responses. The method generates an evaluation result for the HCIR system for the query difficulty level based on the one or more natural language responses, the set of search results, and the set of feedback cues.

Abstract: A system, product, and method are provided for improving knowledge graph (KG) link prediction using transformer-based artificial neural networks. A first topic model is leveraged against a first dataset derived from a KG containing a plurality of first triples. The first triples include first entities and first edges connecting the first entities to represent relationships between the first connected entities. A first similarity function is applied to the first connected entities of the first triples to provide respective first similarity scores. A first subset of one of more first triples is selected from the plurality of first triples based upon the first similarity scores. An artificial neural network is trained using the selected first subset of one or more first triples.

Abstract: A method, a computer system, and a computer program product for building pre-trained contextual embeddings is provided. Embodiments of the present invention may include collecting programming code. Embodiments of the present invention may include loading and preparing the programming code using a specialized programming language keywords-based vocabulary. Embodiments of the present invention may include creating contextual embeddings for the programming code. Embodiments of the present invention may include storing the contextual embeddings.

Abstract: Embodiments of the present invention provide a computer system, a computer program product, and a method that comprises analyzing a performed query by identifying a plurality of indicative markers based on a pre-stored classification database associated with the performed query; generating a plurality of facets based on the analysis of the performed query; selecting at least two facets within the generated plurality of facets by determining a quantitative similarity value between each respective facet and the plurality of identified indicative markers associated with the performed query; dynamically ranking the selected facets by prioritizing the selected facets based on a calculated overall score associated with assigned weighted values for each selected facet in the generated plurality of facets using a supervised machine learning algorithm; and displaying the dynamically ranked facets within a user interface of a computing device associated with a user.

Abstract: A computer-implemented method according to one embodiment includes identifying a natural language query; translating the natural language query into an intermediate representation; converting the intermediate representation into one or more query triples; and performing relation linking between each of the one or more query triples and a plurality of knowledge base triples.

Abstract: A method, system, and computer program product for automated evaluation of information retrieval systems are provided. The method accesses a natural language query from a set of natural language queries. The natural language query is associated with a query difficulty level. The method generates one or more natural language responses to the natural language natural language query. Each natural language response is associated with at least one facet of the plurality of facets. The method generates a set of feedback cues. A set of search results for the natural language query are returned. The set of search results include a highest ranked natural language response of the one or more natural language responses. The method generates an evaluation result for the HCIR system for the query difficulty level based on the one or more natural language responses, the set of search results, and the set of feedback cues.

Abstract: A method, a computer system, and a computer program product for building pre-trained contextual embeddings is provided. Embodiments of the present invention may include collecting programming code. Embodiments of the present invention may include loading and preparing the programming code using a specialized programming language keywords-based vocabulary. Embodiments of the present invention may include creating contextual embeddings for the programming code. Embodiments of the present invention may include storing the contextual embeddings.

Abstract: A method, a computer system, and a computer program product for vulnerability analysis using contextual embeddings is provided. Embodiments of the present invention may include collecting labeled code snippets. Embodiments of the present invention may include preparing the labeled code snippets. Embodiments of the present invention may include tokenizing the labeled code snippets. Embodiments of the present invention may include fine-tuning a model. Embodiments of the present invention may include collecting unlabeled code snippets. Embodiments of the present invention may include predicting a vulnerability of the unlabeled code snippets using the model.

Abstract: One embodiment of the invention provides a method for terminology ranking for use in natural language processing. The method comprises receiving a list of terms extracted from a corpus, where the list comprises a ranking of the terms based on frequencies of the terms across the corpus. The method further comprises accessing a domain ontology associated with the corpus, and re-ranking the list based on the domain ontology. The resulting re-ranked list comprises a different ranking of the terms based on relevance of the terms using knowledge from the domain ontology. The method further comprises generating clusters of terms via a trained model adapted to the corpus, and boosting a rank of at least one term of the re-ranked list based on the clusters to increase a relevance of the at least one term using knowledge from the trained model.

Abstract: A computer-implemented method for performing cross-document coreference for a corpus of input documents includes determining mentions by parsing the input documents. Each mention includes a first vector for spelling data and a second vector for context data. A hierarchical tree data structure is created by generating several leaf nodes corresponding to respective mentions. Further, for each node, a similarity score is computed based on the first and second vectors of each node. The hierarchical tree is populated iteratively until a root node is created. Each iteration includes merging two nodes that have the highest similarity scores and creating an entity node instead at a hierarchical level that is above the two nodes being merged. Further, each iteration includes computing the similarity score for the entity node. The nodes with the similarity scores above a predetermined value are entities for which coreference has been performed in input documents.

Abstract: Aspects of the invention include a system, a computer program product and a computer-implemented method for building a relational database between a first term and a second term. An embedding management system is used to determine a first term set based on the first term and a second term set based on the second term. An entity linking engine and a knowledge base engine are used to determine a relation match for the first term set when a relation of the first term set relates to a term from a second term set and for determining a relation match for the second term set when a relation of the second term set relates to a term from a first term set. A relation ranking engine selects a relation for the relational database having a selected number of matches.

Abstract: A computer-implemented method according to one embodiment includes converting an input question into a vector form using trained word embeddings; constructing a type similarity matrix using a predetermined ontology; and determining a score for all possible types for the input question, based on the input question in vector form and the type similarity matrix.