International Business Machines Corporation

University of Massachusetts

Nternational Business Machines Corporation

Michael Robert Glass

Alfio Massimiliano Gliozzo

Md Faisal Mahbub Chowdhury

Gaetano Rossiello

James W Murdock, Iv

Mustafa Canim

Sarthak Dash

Md Faisal M Chowdhury

Robert G Farrell

Parijat Dube

Bishwaranjan Bhattacharjee

Aditya Anand Kalyanpur

James J Fan

Benjamin P Segal

Adam P Lally

Patrick D Watson

Matthew Leon Hill

John Ronald Kender

Noel C Codella

Michael A Barborak

Siyu Huo

Nandana Sampath Mihindukulasooriya

Nicholas Brady Garvan Monath

Brian Michael Belgodere

Nicolas Rodolfo Fauceglia

Md Arafat Sultan

Ankita Rajaram Naik

Xueqing Wu

Faisal Mahbub Chowdhury

Using a trained keyphrase generation model, a set of keyphrases corresponding to an input document is generated, a keyphrase in the set of keyphrases comprising a word summarizing a portion of a document. A relevance score measuring a similarity between the keyphrase and the document is calculated for a keyphrase in the set of keyphrases. The relevance score is adjusted according to a diversity balancing function.

Keyphrase generation

An embodiment includes generating a training dataset by aligning text from a document of a document database with a named entity from a knowledge base. The embodiment generates an enhanced training dataset by updating the training dataset to include a named entity type and a named entity label associated with the named entity. The embodiment trains a natural language processing (NLP) model using the enhanced training dataset resulting in a trained NLP model. The embodiment identifies, using the trained NLP model, the named entity in a block of unstructured text and generates, using the trained NLP model, a target sequence that includes a relationship between the named entity and a tail entity, as well as the named entity type and the named entity label of the named entity and a tail entity type and a tail entity label of the tail entity.

Generating semantic triplets from unstructured text using named entities

Embodiments of the invention are directed to a computer system comprising a memory communicatively coupled to a processor system. The processor system is operable to perform processor system operations that include accessing query information associated with a to-be-augmented information set (TBAIS) having a TBAIS format. Query information sequence vectors (QISV) are generated that represent the query information and the TBAIS. Unannotated data repository information sequence vectors (UDRSV) are accessed that represent unannotated data repository information having a plurality of information formats. Matching UDRSV are identified, where the matching UDRSV include the UDRSV that match the QISV. A response to the query information is generated based at least in part on the matching UDRSV.

Retrieval-based, self-supervised augmentation using transformer models

Determining an initial rank and a probability of relevance of each of a retrieved plurality of electronic documents relevant to a query. For each of a plurality of candidate facets, determine a revised rank for each of the retrieved plurality of electronic documents relevant to the query. Selecting, for each of the retrieved plurality of electronic documents relevant to the query, a minimum rank from among the initial rank and the revised rank for each of the plurality of candidate facets. Determine an expected discounted cumulative gain based on the probability of relevance and the minimum rank for each of the retrieved plurality of electronic documents relevant to the query. Select a set of optimistic facets based on maximizing the expected discounted cumulative gain.

Optimistic facet set selection for dynamic faceted search

One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to a process for generating the classification of files to allow for file system organization and/or query augmentation. 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 generating component that generates a keyphrase based on a context derived from evaluation of an input file, wherein the generating component employs a public repository of files annotated with a plurality of keyphrases, including the keyphrase, to generate the keyphrase based on the context, and an execution component that classifies the input file based on the keyphrase. In one or more embodiments, the input file can comprise a query, and classification of the input file can comprise augmenting the query based on the keyphrase.

Keyphrase generation leveraging public repository categories

A computer answers a question using a data table. The computer receives a user question and a target table containing a target cell corresponding to a target answer for the user question, with the target cell corresponding to a target column and a target row. The computer generates, a first classifier to provide column correlation values reflecting the probability that a given column is the target column. The computer generates a second classifier that provides row correlation values reflecting the probability that a given row is the target row. The computer applies the first classifier to the target table to determine a column correlation value for each column. The computer applies the second classifier to the target table to determine a row correlation value for each row. The computer suggests, as the target cell, a cell having elevated column and row correlation values relative to other target table cells.

Answering questions with artificial intelligence using tabular data

A system comprises a memory that stores computer-executable components; and a processor, operably coupled to the memory, that executes the computer-executable components. The system includes a receiving component that receives a corpus of data; a relation extraction component that generates noisy knowledge graphs from the corpus; and a training component that acquires global representations of entities and relation by training from output of the relation extraction component.

Deep symbolic validation of information extraction systems

Whether to train a new neural network model can be determined based on similarity estimates between a sample data set and a plurality of source data sets associated with a plurality of prior-trained neural network models. A cluster among the plurality of prior-trained neural network models can be determined. A set of training data based on the cluster can be determined. The new neural network model can be trained based on the set of training data.

Training transfer-focused models for deep learning

Methods and systems are described for populating knowledge graphs. A processor can identify a set of data in a knowledge graph. The processor can identify a plurality of portions of an unannotated corpus, where a portion includes at least one entity. The processor can cluster the plurality of portions into at least one data set based on the at least one entity of the plurality of portions. The processor can train a model using the at least one data set and the set of data identified from the knowledge graph. The processor can apply the model to a set of entities in the unannotated corpus to predict unary relations associated with the set of entities. The processor can convert the predicted unary relations into a set of binary relations associated with the set of entities. The processor can add the set of binary relations to the knowledge graph.

Unary relation extraction using distant supervision

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.

Encoding entity representations for cross-document coreference

Methods and systems for natural language processing include pretraining a machine learning model that is based on a bidirectional encoder representations from transformers model, using a span selection training data set that associates a masked word with a passage. A natural language processing task is performed using the span selection pretrained machine learning model.

Span selection training for natural language processing

Training a machine learning model such as a neural network, which can automatically extract a hypernym from unstructured data, is disclosed. A preliminary candidate list of hyponym-hypernym pairs can be parsed from the corpus. A preliminary super-term&#x2014;sub-term glossary can be generated from the corpus, the preliminary super-term&#x2014;sub-term glossary containing one or more super-term&#x2014;sub-term pairs. A super-term&#x2014;sub-term pair can be filtered from the preliminary super-term&#x2014;sub-term glossary, responsive to detecting that the super-term&#x2014;sub-term pair is not a candidate for hyponym-hypernym pair, to generate a final super-term&#x2014;sub-term glossary. The preliminary candidate list of hyponym-hypernym pairs and the final super-term&#x2014;sub-term glossary can be combined to generate a final list of hyponym-hypernym pairs. An artificial neural network can be trained using the final list of hyponym-hypernym pairs as a training data set, the artificial neural network trained to identify a hypernym given new text data.

Unsupervised hypernym induction machine learning

Techniques regarding similarity based negative sample analysis are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a similarity component that can determine similarity metrics for respective entities based on a vector space model. The respective entities can be represented by a dataset. Also, the computer executable components can comprise a sampling component that can perform a negative sampling analysis on the dataset based on the similarity metrics.

Similarity based negative sampling analysis

A method, system and computer program product for recognizing terms in a specified corpus. In one embodiment, the method comprises providing a set of known terms t&#x2208;T, each of the known terms t belonging to a set of types &#x393; (t)={&#x3b3;, . . . }, wherein each of the terms is comprised of a list of words, t=w, w, . . . , w, and the union of all the words for all the terms is a word set W. The method further comprises using the set of terms T and the set of types to determine a set of pattern-to-type mappings p&#x2192;&#x3b3;; and using the set of pattern-to-type mappings to recognize terms in the specified corpus and, for each of the recognized terms in the specified corpus, to recognize one or more of the types &#x3b3; for said each recognized term.

Growing community of inventors

Bayonne, NJ, United States of America

Michael Robert Glass