Abstract: Aspects of the invention include receiving a search query from a user computing device. Retrieving a set of passages based on the search query, wherein each passage contains passage evidence and an annotation embedded as metadata. Scoring each annotation and each passage evidence, where each annotation score is based on a feature vector of the annotation and the search query, and where each passage evidence score is based on a feature vector of the passage evidence and the search query. Ranking each passage based on a passage evidence score and a score of one annotation contained in the passage. Returning a ranked list of each passage to the user computing device.

Abstract: Embodiments include cross-document propagation of entity metadata. Aspects include identifying a set of documents from a plurality of documents, the set of documents being related to one another and identifying a concept in a first document of the set of documents and creating an annotation corresponding to the concept. Aspects also include evaluating the annotation from the first document against all of the documents in the set of documents and identifying a concept match between the annotation and a mention discovered in a second document in the set of documents. Aspects further include creating a metadata linkage between the concept in the first document to the mention in the second document.

Abstract: Techniques for targeted partial re-enrichment include determining that at least one natural language processing (NLP) request is associated with at least one surface form, the NLP request being for a corpus, a database comprising preexisting annotations associated with the corpus. An index query related to the at least one surface form is performed to generate index query results, the index query results including identification of portions of the corpus affected by the NLP request. A scope of the NLP request related to the database is determined based on the index query results, the scope including identification of impacted candidate annotations of the preexisting annotations affected by the NLP request. An NLP service is performed on the corpus according to the scope and the portions, thereby resulting in updates. The updates are committed to the database associated with the corpus.

Abstract: Techniques for concept disambiguation for natural language processing are described herein. An aspect includes receiving a message from a user. Another aspect includes identifying an ambiguous concept in the message. Another aspect includes determining a plurality of concept candidates corresponding to the ambiguous concept. Another aspect includes determining, for each of the plurality of concept candidates, a respective similarity score based on user-specific concept metrics corresponding to the user. Another aspect includes ranking the plurality of concept candidates based on the respective similarity scores. Another aspect includes determining that the ambiguous concept corresponds to a top-ranked concept candidate of the ranked plurality of concept candidates.

Abstract: Aspects of the invention include converting text from a first image file into a first machine-encodable text, wherein the image file includes a first section of text that is offset from a second section of text. Analyzing the first image file to detect a position of the first section of text. Embedding a first section of the first machine encodable-text with metadata describing the position of the first section of text. Reformatting the first section of the first machine encodable-text to conform to the position of the first section of text.

Abstract: Examples described herein provide a computer-implemented method that includes receiving a ground truth associated with a domain cartridge, the domain cartridge comprising a plurality of hierarchical layers. The method further includes analyzing annotation blocks in relation to data present in the ground truth to detect any errors in a set of natural language processing annotators. The analyzing includes computing a recall score, a precision score, and an F1 score for each annotation block in a lowest level layer of the plurality of hierarchical layers. The analyzing further includes determining whether an error is detected at the lowest level layer of the plurality of hierarchical layers based at least in part on the recall score, the precision score, and the F1 score. The analyzing further includes terminating the analyzing responsive to determining that the error is detected at the lowest level layer of the plurality of hierarchical layers.

Abstract: Aspects of the invention include systems and methods for the propagation of annotation metadata to overlapping annotations of a synonymous type. A non-limiting example computer-implemented method includes performing a comparison of a set of annotations to detect a subset of annotations that are candidates of being synonymous based on a first analysis. Whether a first annotation of the subset of annotations is synonymous with a second annotation of the subset of annotations is determined based on a second analysis. Distinct annotation metadata of the first annotation are cross-propogated with annotation metadata of the second annotation based on the second analysis.

Abstract: Aspects of the disclosure include receiving, by a processor, a plurality of documents, each document in the plurality of documents comprising metadata, defining, by the processor, a target attribute comprising a set of annotations and a set of cross-document configuration requirements, ingesting the plurality of documents based on the target attribute to identify one or more annotations from the set of annotations in the plurality of documents that comply with the set of cross-document configuration requirements, storing in a memory, during the ingesting the plurality of documents, the identified one or more annotations, and returning the identified one or more annotations to a user.

Abstract: Embodiments include methods, system and computer program products for processing a scanned document. Aspects include obtaining an image of the scanned document and identifying a boundary of a portion of the scanned document, wherein the portion includes at least partially obscured text. Aspects also include performing optical character recognition on the image of the scanned document to extract text from the document. Aspects further include performing additional processing on the text extracted from inside the portion of the document.

Abstract: Aspects of the present disclosure describe techniques for generating a machine learning model for extracting information from textual content. The method generally includes receiving an unstructured document and a structured document including information extracted from the unstructured document and position information associated with the extracted information. The unstructured document is rendered in a first pane, and a graphical rendering of the structured document is rendered in a second pane. The graphical rendering generally may be a structure in which content from the structured document is displayed in a hierarchical format. Each element in the structured document is linked to the rendered unstructured document based on position information included in the structured document.

Abstract: Aspects of the present disclosure describe techniques for generating a machine learning model for extracting information from textual content. The method generally includes receiving a training data set including a plurality of documents having related textual strings. A relevancy model is generated from the training data set. The relevancy model is generally configured to generate relevance scores for a plurality of words extracted from the plurality of documents. A knowledge graph model illustrating relationships between the plurality of words extracted from the plurality of documents is generated from the training data set. The relevancy model and the knowledge graph model are aggregated into a complimentary model including a plurality of nodes from the knowledge graph model and weights associated with edges between connected nodes, wherein the weights comprise relevance scores generated from the relevancy model, and the complimentary model is deployed for use in analyzing documents.

Abstract: The exemplary embodiments disclose a system and method, a computer program product, and a computer system for modifying multimedia. The exemplary embodiments may include receiving a multimedia and one or more inputs, determining a required amount of modification to the multimedia based on the one or more inputs, generating a literary parse tree based on the multimedia, extracting one or more node features from one or more nodes of the parse tree, determining a node importance of the one or more nodes based on applying a model to the one or more node features, and modifying one or more portions of the multimedia corresponding to the one or more nodes based on the node importance and the required amount of multimedia modification.

Abstract: A method for generating and presenting a comment excerpt in an online publication based on a comment in a comments section is provided. The method may include determining whether a passage from the comment in the comments section is relevant to a sentence in the online publication, and in response to determining that the passage from the comment is relevant to the sentence in the online publication, extracting the passage from the comment. The method may further include determining the scope of the comment that is associated with the extracted passage, wherein determining the scope of the comment comprises determining a context associated with the extracted passage based on text surrounding the extracted passage. The method may further include, based on the determined scope of the comment, generating the comment excerpt that corresponds to the comment. The method may further include presenting the comment excerpt within the online publication.

Abstract: The exemplary embodiments disclose a system and method, a computer program product, and a computer system for determining the intents of user expression. The exemplary embodiments may include receiving a user expression, extracting one or more entities from the user expression, gathering one or more resolvers associated with the one or more entities, identifying a first resolver of the one or more resolvers based on the user expression and the one or more training expressions, and resolving the first resolver to generate a first output.

Abstract: The exemplary embodiments disclose a system and method, a computer program product, and a computer system for resolving the intents of user expression. The exemplary embodiments may include receiving a user expression, receiving a first resolver having an input class and an output class based on the user expression, determining whether the first resolver can be resolved based on the user expression, and based on determining that the first resolver can be resolved based on the user expression, resolving the first resolver.

Abstract: Examples described herein provide a computer-implemented method that includes receiving a ground truth associated with a domain cartridge, the domain cartridge comprising a plurality of hierarchical layers. The method further includes analyzing annotation blocks in relation to data present in the ground truth to detect any errors in a set of natural language processing annotators. The analyzing includes computing a recall score, a precision score, and an F1 score for each annotation block in a lowest level layer of the plurality of hierarchical layers. The analyzing further includes determining whether an error is detected at the lowest level layer of the plurality of hierarchical layers based at least in part on the recall score, the precision score, and the F1 score. The analyzing further includes terminating the analyzing responsive to determining that the error is detected at the lowest level layer of the plurality of hierarchical layers.

Abstract: Examples described herein provide a computer-implemented method that includes receiving, by a processing device, the span of text, the span of text comprising a plurality of elements including at least an entity element and a temporal element. The method further includes organizing, by the processing device, the span of text as a natural language processing (NLP) parse tree. The method further includes traversing, by the processing device, the NLP parse tree by concatenating individual nodes of the span of text to generate the relation type between the entity element and the temporal element. The method further includes associating, by the processing device, the entity element, the relation type, and the temporal element together.

Abstract: Aspects of the invention include systems and methods for the propagation of annotation metadata to overlapping annotations of a synonymous type. A non-limiting example computer-implemented method includes performing a comparison of a set of annotations to detect a subset of annotations that are candidates of being synonymous based on a first analysis. Whether a first annotation of the subset of annotations is synonymous with a second annotation of the subset of annotations is determined based on a second analysis. Distinct annotation metadata of the first annotation are cross-propogated with annotation metadata of the second annotation based on the second analysis.

Abstract: A method for generating and presenting a comment excerpt in an online publication based on a comment in a comments section is provided. The method may include determining whether a passage from the comment in the comments section is relevant to a sentence in the online publication, and in response to determining that the passage from the comment is relevant to the sentence in the online publication, extracting the passage from the comment. The method may further include determining the scope of the comment that is associated with the extracted passage, wherein determining the scope of the comment comprises determining a context associated with the extracted passage based on text surrounding the extracted passage. The method may further include, based on the determined scope of the comment, generating the comment excerpt that corresponds to the comment. The method may further include presenting the comment excerpt within the online publication.

Abstract: Embodiments include methods, system and computer program products for processing a scanned document. Aspects include obtaining an image of the scanned document and identifying a boundary of a portion of the scanned document, wherein the portion includes at least partially obscured text. Aspects also include performing optical character recognition on the image of the scanned document to extract text from the document. Aspects further include performing additional processing on the text extracted from inside the portion of the document.