International Business Machines Corporation

Hangu Yeo

Vadim Sheinin

Octavian Popescu

Elahe Khorasani

Ngoc Phuoc An Vo

Jeffrey Haskell Derby

Moon Jung Kim

Yumi Mori

Munehiro Doi

Irene Lizeth Manotas Gutiérrez

A set of values can be selected from a plurality of fields of a table in a database. At least one adverb or adjective can be selected for the set of values. Join paths for values in the set of values can be determined. A structured query language pattern can be determined based, at least in part, on at least one value in the set of values, the at least one adverb or adjective for the set of values, and the join paths for the set of values. The structured query language pattern can be stored to first training data configured, at least in part, for use in machine learning to train a text-to-SQL model, the text-to-SQL model comprising a first artificial neural network and configured to convert first natural language text to a first structured query language query.

Generating training data for a machine learning model that performs text-to-SQL

Various embodiments are provided herein for decreasing a central processing unit (CPU) inference time, thereby shortening processing time of a deep learning model for which run-time complexity is proportional to an output sequence length. A compacted sequence is developed that is used to train the deep learning model. An output of the trained model becomes the compacted sequence on which a post-processing method operates to create an uncompacted version of a predicted sequence.

Reducing inference time processing deep learning models

A method, system and apparatus of processing queries, including inputting a query as query data, generating paraphrases from the query data, and normalizing the generated paraphrases according to predefined annotations of a schema.

Accuracy of QA systems by normalizing logical queries

An embodiment for identifying and replacing logically neutral phrases in natural language queries may include receiving a natural language query. The embodiment may also identify one or more logically neutral or non-logically neutral anchors in the natural language query. The embodiment may also identify boundaries containing one or more logically neutral phrases. The embodiment may further include detecting semantic and logical relations between verbal phrases and functional language between and adjacent to the one or more logically neutral and non-logically neutral anchors to reintroduce non-logically neutral language back into a non-logically neutral portion of the natural language query. The embodiment may also include generating a modified natural language query by automatically removing the boundaries and optionally replacing the one or more logically neutral phrases in the natural language query. The embodiment may further include providing the modified natural language query to a query processing system for further processing.

Identifying and replacing logically neutral phrases in natural language queries for query processing

A computer-implemented method, a computer system and a computer program product create rules for a rule-based natural language interface for databases (NLIDB). The method may include receiving a natural language query from a user. The method may also include generating a first explanation for the natural language query using a deep learning model and a second explanation for the natural language query using the rule-based NLIDB and validating whether the first and second explanations correctly represent the natural language query. The method may further include identifying the database value in the first explanation in response to the first explanation correctly representing the natural language query and the second explanation not correctly representing the natural language query. Lastly, the method may include creating a rule in a table for the rule-based natural language interface for databases that associates the database value with the original word of the natural language query.

Refining understanding of natural language database queries

Methods, systems and computer readable media are provided for automatically creating a semantic model of a relational database for processing natural language queries. A computing device automatically extracts relational database metadata. The computing device prompts a user to enter textual labels for columns of the extracted metadata. The computing device automatically generates a schema annotation file based upon the relational database metadata and the textual labels for the columns. A natural language query is processed for the relational database using the schema annotation file.

Automatic creation of schema annotation files for converting natural language queries to structured query language

A system for responding to natural language medical queries is provided. The system includes a memory storing a computer program and a processor configured to execute the computer program. The computer program decomposes an input medical related user query into medical related sub-queries using pre-defined proxies, rephrases the sub-queries into yes-no queries answerable with a yes or a no, extracts feature values from the yes-no queries and a relational database storing clinical records, generates a feature vector from the extracted feature values, and applies the feature vector along with desired output labels to a supervised machine learning algorithm to generate a classifier configured to answer a new medical related user query.

System for responding to complex user input queries using a natural language interface to database

There is provided an apparatus and a processor-implemented method. The method includes aligning a reference genome with a plurality of DNA sequences. Each of the plurality of DNA sequences has a respective plurality of bases. The method further includes classifying and sorting the plurality of read sequences based on respective numbers of mismatched bases within the plurality of read sequences to obtain a plurality of re-arranged DNA sequences. The method also includes building a histogram based on respective positions of mismatched bases within the plurality of re-arranged DNA sequences. The method additionally includes coding at least some of the plurality of re-arranged DNA sequences based on the histogram.

Lossless compression of DNA sequences

Techniques for implementing mixed-radix FFT on SIMD vector processors efficiently for the latest standard in wireless communication technology by dynamically reordering stages are provided. In one aspect, a mixed-radix FFT implementation method for vector processors is provided which includes the following steps. Input data is decomposed into segments of factors based on a size of the input data, wherein the decomposing is performed in one or more stages, and wherein at each of the stages the input data is processed in blocks using one or more FFT butterfly computations for each of the blocks. The stages in which the decomposing is performed are reordered to insure complete utilization of the vector processors. The butterfly computations for one or more of the blocks are reordered to insure that the input data have memory addresses which are next to each other and contiguous.

Techniques for improving the efficiency of mixed radix fast fourier transform

The present approach increases bandwidth by performing at least two functions at the pre-processing level. Specifically, under the present approach, program code is structured so that the segmentation and binarization functions/modules (and optionally a blob analysis function/module) are merged into a single module to reduce memory bandwidth. In addition, each image frame is segmented into a plurality of partitions (e.g., vertical strips) to enhance the reusability of the image data in LS already fetched from main memory. Each partition is then processed by a separate one of a plurality of processing engines, thereby increasing the utilization of all processing engines and allowing the processing engines to maintain good bandwidth.

Growing community of inventors

Baldwin Place, NY, United States of America

Hangu Yeo