International Business Machines Corporation

Google Inc.

Vadim Sheinin

Octavian Popescu

Ligang Lu

Hangu Yeo

Elahe Khorasani

Dake He

Ngoc Phuoc An Vo

Ashish Jagmohan

Petros Zerfos

Irene Lizeth Manotas Gutiérrez

Brent Paulovicks

Jeffrey Haskell Derby

Lingfei Wu

Branimir Konstantinov Boguraev

Ta-Hsin Li

Elham Khabiri

Aditya Vempaty

Siddharth A Patwardhan

Kun Xu

Matthew Daniel Riemer

Swapna Buccapatnam Tirumala

Zhiguo Wang

Krishna Chaitanya Ratakonda

Tin Kam Ho

Michael Peter Perrone

Cesar Augusto Gonzales

Bijan Davari

Gheorghe Almasi

Jack Lawrence Kouloheris

Jun Chen

Algimantas Černiauskas

A natural language processor and applicable method receives an input sentence of natural language from a natural language corpus. The input sentence comprises sentence clauses that include a conditional clause. The processor performs natural language processing (NLP), using an NLP model, on the input sentence. The processing comprises using a set of rules determining the sentence clauses and which of the sentence clause is the conditional clause, determining one or more logical connections between the sentence clauses, and determining a role of the sentence clauses based upon the one or more identified logical connections. The sentence clauses are tagged to produce a labeled sentence that is output to an entity that is one or more of a storage device, a network interface, a storage device, and an input of a further language processor or application.

Logical role determination of clauses in conditional constructions of natural language

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 of authoring a conversation service for a chatbot and a database includes receiving, from a user, a selection of a database, and connecting an authoring service of the chatbot to a table in the database; outputting, from the authoring service to the user, a question requesting a description of a subject matter of the table; receiving the description of the subject matter of the table; outputting to the user a question requesting an identification of a key column of the table that contains values that represent the subject matter of the table; receiving the identification of the key column of the table; and translating, by a natural language query service, the description of the subject matter of the table and the key column of the table into the conversation service, wherein the conversation service includes SQL statements suitable for querying the database table.

Authoring a conversation service module from relational data

A computer system extracts clauses using machine translation. An input sentence in a source language is translated into a translated sentence in a target language using a trained machine translation model, wherein the trained machine translation model inserts a grammatical indicator into a position of the translated sentence that identifies a dependent clause. The input sentence and the translated sentence are aligned to determine a position in the input sentence that corresponds to the position of the grammatical indicator in the translated sentence. The dependent clause is extracted, in the source language, from the input sentence based on the determined position in the input sentence. Embodiments of the present invention further include a method and program product for clause extraction using machine translation in substantially the same manner described above.

Clause extraction using machine translation and natural language processing

An embodiment of the present invention is a prime representation data structure in a computer architecture. The prime representation data structure has a plurality of records where each record contains a prime representation and where the prime representation is a product of two or more selected prime factors. Each of the selected prime factor associated with an n-gram of a domain representation of a domain string. The domain representation of the domain string is a domain string of ordered, contiguous domain characters. The n-gram being a subset of n number of the ordered, contiguous domain characters in the domain string. The computer architecture performs string searching and includes one or more central processing units (CPUs) with one or more operating systems, one or more input/output device interfaces, one or more memories, and one or more input/output devices. The architecture further includes the prime representation data structure, one or more prime target query data structures and a search process performed by one or more of the CPUs. The CPUs can be organized in a hierarchical structure. The prime target query data structure has one or more target prime queries. Each target prime query is the product of one or more target selected prime factors. Each target selected factor is associated with a target n-gram of a target domain representation of a target domain string. The search process, performed by one or more of the CPUs, determines whether one or more of the target selected prime factors is common with one of the selected prime factors. By performing this efficient testing, the computer system can determine if one or more small strings are included in one or more large strings.

Computer architecture for string searching

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 method (and structure and computer product) of machine translation for processing input questions includes receiving, in a processor on a computer, an input question presented in a natural language. The input question is preprocessed to find one or more condition values for possible Structured Query Language (SQL) queries. One or more possible SQL queries are enumerated based on the one or more found condition values and a paraphrasing model is used to rank the enumerated SQL queries. The highest ranked SQL query is executed against a relational database to search for a response to the input question.

Natural language to structured query generation via paraphrasing

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

Techniques for mapping policy documents to regulatory documents to check for compliance between the policies and documents are provided. In one example, a computer-implemented method determining, by a system operatively coupled to a processor, an information input, a control framework, and a document from a first group consisting of a regulatory document and a policy document, wherein the information input is a corpora from a second group consisting of a domain corpora and a global corpora. The computer-implemented method can also comprise mapping, by the system, the received regulatory document or the received policy document to the control framework using a supervised machine learning technique.

Facilitating mapping of control policies to regulatory documents

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 corpus pattern paraphrasing method, system, and non-transitory computer readable medium, include aligning slots of patterns for verbal phrases based on syntactical and lexical features along with calculated synonyms to predict paraphrases that are not previously stored in a corpus of sentences in a database.

System, method, and recording medium for corpus pattern paraphrasing

Methods, systems, and computer program products for extracting meaning representation from text are provided herein. A computer-implemented method includes performing a syntactic analysis on a fragment of text to derive a syntactic structure; selecting one or more predefined syntactic structure templates corresponding to the derived syntactic structure that define different combinations of semantic primes and semantic features corresponding to the semantic primes; detecting semantic information in the fragment of text, wherein the semantic information comprises at least one of the semantic primes and one or more of the corresponding semantic features; identifying one of the selected predefined syntactic structure templates that matches the derived syntactic structure and the detected semantic information in the fragment of text; generating a computable meaning representation of the fragment of text based at least in part on the identifying; and outputting the computable meaning representation to a natural language understanding application.

Growing community of inventors

Yorktown Heights, NY, United States of America

Vadim Sheinin