International Business Machines Corporation

Globalfoundries Inc.

University of Michigan

Yunyao Li

Huaiyu Zhu

Shivakumar Vaithyanathan

Laura Chiticariu

Huahai Yang

Benny Kimelfeld

Prithviraj Sen

Marina Danilevsky Hailpern

Rajasekar Krishnamurthy

Eser Kandogan

Sriram Raghavan

Mauricio Antonio Hernandez-Sherrington

Liang Gou

Kun Qian

Siddhartha Brahma

Alan Akbik

Adriano Crestani Campos

Min Li

David Everett Simmen

Michelle Xue Zhou

Hao Wang

Ching-Tien Ho

Frederick Ralph Reiss

Dimple Bhatia

Armageddon Rhabdizo Brown

Tyler Shore Baldwin

Margaret Zagelow

Arnaldo Carreno-Fuentes

Suresh Thalamati

Jayatheerthan Krishnamurthy

Mengdie Hu

Ramiya Venkatachalam

Chenguang Wang

Ishan Jindal

Zhuowei Bao

Sang Don Han

Nikita Bhutani

Xin Ru Wang

Dakshi Agrawal

Shankar Venkataraman

Dulce Beatriz Ponceleon

Taiga Nakamura

Hosagrahar Visvesvaraya Jagadish

Anbang Xu

Lucian Popa

Ioana Roxana Stanoi

Peifeng Yin

Douglas Ronald Burdick

Eben Merriam Haber

Sara A Noeman

Christopher Palmer

Jerome M Pesenti

Ioannis Katsis

Christine T Wolf

Sebastian Johannes Blohm

Bogdan Alexe

Ching-Tien (Howard) Ho

Sairam Gurajada

Sanjana Sahayaraj

Marie Louise Elizabeth Van Der Plas

Carlos Fernando Diez Sánchez

George A Cypher

Jungo Kasai

Michael James Wehar

Zhichao Hu

Yiwei Yang

Victor K Ondego

Christopher J Baik

Congle Zhang

Zihui Li

Vijaykumar R Bommireddipalli

Richard S Maraschi

Ah-Fung Sit

Rajasekar Krishmamurthy

Vivian Yaw-Wen Chu

Honglei Zhuang

Aparna Garimella

Poornima Chozhiyath Raman

A system, computer program product, and method are provided for jointly learning dictionary based rules and dictionary candidates. Natural language text is received and parsed into subsets, with the subset being subjected to natural language processing to identify one or more verbs within the subset. The identified verbs are evaluated with respect to a dictionary and one or more rules. The evaluation is directed at each predicate in the rules with respect to the identified verbs. A neural network is leveraged to jointly induce modification of the rules and one or more dictionaries responsive to the evaluation.

Learning rules and dictionaries with neuro-symbolic artificial intelligence

Systems and techniques that facilitate parameterized neighborhood memory adaptation for semantic role labeling are provided. In various embodiments, a system can comprise a receiver component that can access a semantic role labeling model trained on a training dataset. In various aspects, the system can further comprise an execution component that can retrain a labeler of the semantic role labeling model based on a set of neighborhood parameters learned from the training dataset. In various instances, the execution component can execute, after retraining, the semantic role labeling model on an inputted sentence.

Parameterized neighborhood memory adaptation

A computer-implemented method according to one embodiment includes receiving, at a scheduler, a training data instance and a target instance, generating, by the scheduler, an input sequence from the training data instance and the target instance, sending the input sequence from the scheduler to an encoder, mapping, by the encoder, the input sequence to a feature vector, sending the feature vector from the encoder to the scheduler, sending the feature vector from the scheduler to a predictor, and mapping, by the predictor, the feature vector to a class vector to create a label for the target instance.

Predicting functional tags of semantic role labeling

One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to regularizing semantic similarity relationships relative to a pair of languages. 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 comprise a computation component that generates a transformation comprising a semantic similarity relationship between detected semantic labels of a pair of languages.

Determining semantic relationships of argument labels

A computer-implemented method according to one embodiment includes receiving a plurality of linguistic expressions (LEs); changing one or more conditions of the plurality of linguistic expressions to create an updated plurality of linguistic expressions, utilizing a visual exploration framework (VEF) that visually presents to a user each of the plurality of linguistic expressions; and including the updated plurality of linguistic expressions in a model used to classify input sentences. According to another embodiment, a computer-implemented method includes receiving (i) a set of linguistic expressions (LEs) and (ii) a set of labeled data as input, where the LEs are logical combinations of predicates learned from the labeled data, and each data point in the labeled data comprises a piece of text and ground-truth labels; presenting the LEs in a visual exploration framework; and allowing a user to sort, filter, subset, and select LEs based on different criteria, utilizing the framework.

Adjusting explainable rules using an exploration framework

A computer-implemented method according to one embodiment includes receiving, at a deep neural network (DNN), a plurality of sentences each having an associated label; training the DNN, utilizing the plurality of sentences and associated labels; and producing a linguistic expression (LE) utilizing the trained DNN.

Producing explainable rules via deep learning

Methods, systems, and computer program products for low-resource entity resolution with transfer learning are provided herein. A computer-implemented method includes processing input data via a first entity resolution model, wherein the input data comprise labeled input data and unlabeled input data; identifying one or more portions of the unlabeled input data to be used in training a neural network entity resolution model, wherein said identifying comprises applying one or more active learning algorithms to the first entity resolution model; training, using (i) the one or more portions of the unlabeled input data and (ii) one or more deep learning techniques, the neural network entity resolution model; and performing one or more entity resolution tasks by applying the trained neural network entity resolution model to one or more datasets.

Low-resource entity resolution with transfer learning

Providing a predictive model for a target language by determining an instance weight for a labeled source language textual unit according to a set of unlabeled target language textual units, scaling, by the one or more computer processors, an error between a predicted label for the source language textual unit and a ground-truth label for the source language textual unit according to the instance weight, updating, by the one or more computer processors, network parameters of a predictive neural network model for the target language according to the error, and providing, by the one or more computer processors, the predictive neural network model for the target language to a user.

Zero-shot cross-lingual transfer learning

A computer-implemented method according to one embodiment includes receiving a question in a natural language format; deriving a plurality of subqueries from the question; determining that a first subquery of the plurality of subqueries cannot be resolved utilizing a curated knowledge base; resolving the first subquery, utilizing unstructured text; and adjusting the curated knowledge base, utilizing the resolved first subquery.

Resolving queries using structured and unstructured data

One embodiment provides for a method for evaluation of an artificial intelligence (AI) service, the method includes partitioning, by a processor, data into in-domain data and out-of-domain data. The processor defines held-out data from both of the in-domain data and the out-of-domain data for evaluation by each of domain and sub-domain based on building a taxonomy of both domains and sub-domains for the AI service. The held-out data is excluded from training data used for training the AI service. The processor further determines distribution underlying performance metrics for the held-out data using bootstrap validation processing. The processor also determines performance guarantees for multiple settings conditioned on multiple characteristics of an application scenario for the held-out data of the taxonomy based on the underlying performance metrics.

Workflow for evaluating quality of artificial intelligence (AI) services using held-out data

A computer system, product, and method are provided to utilize machine learning to facilitate document processing. A document collection is introduced to an artificial neural network (ANN), which subjects the document collection to table region identification within discretized contiguous areas. The documents are assigned to one or more clusters responsive to the leveraged ANN. Documents are selectively evaluated from the clusters, and one or more label corrections are applied to the ANN. The ANN generates an updated document collection incorporating the applied one or more label corrections.

Interactive structure annotation with artificial intelligence

A computer-implemented method, according to one embodiment, is for performing review of semantic role labeling resources. The computer-implemented method includes: receiving pairs of automatically projected semantic verb frames, and computing a similarity score for each of the pairs of semantic verb frames. A joint distributional semantic system is trained using the computed similarity scores. Moreover, a determination is made as to whether to merge each pair of the semantic verb frames, by applying the joint distributional semantic system to that pair. In response to determining that a given pair of semantic verb frames should be merged, an indication is provided to a recipient that the given pair of semantic verb frames should be merged.

Using a joint distributional semantic system to correct redundant semantic verb frames

In an approach, a processor trains a statistical classifier and a set of micro classifiers. A processor receives an input to be classified by the statistical classifier. A processor receives a label assigned to the input by the statistical classifier and respective labels assigned by each micro classifier of the set of micro classifiers. A processor determines that the label assigned by the statistical classifier is the same as at least one label assigned by at least one micro classifier of the set of micro classifiers. A processor generates a natural language explanation for assigning the label using the at least one micro classifier and the label. A processor outputs the label and the natural language explanation to a user of a computing device. A processor receives user feedback from the user in the form of an acceptance or a rejection of the natural language explanation.

Natural language explanation for classifier predictions

A computer-implemented method for generating a question from an abstracted template is described. A non-limiting example of the computer-implemented method includes receiving, by a processor, a question. The method parses, by the processor, the question into a parse tree and abstracts, by the processor, an abstracted template from the parse tree. The method receives, by the processor, a domain schema and a domain knowledge base and generates, by the processor, a new question based on the abstracted template, the domain schema, and the domain knowledge base.

Domain-specific labeled question generation for training syntactic parsers

One embodiment provides for a method for evaluation of an artificial intelligence (AI) service, the method includes partitioning, by a processor, data into in-domain data and out-of-domain data. The processor defines held-out data from the in-domain data and the out-of-domain data for evaluation by domain and sub-domain based on building a taxonomy of domains and sub-domains for the AI service. The processor further determines distribution underlying performance metrics for the held-out data using statistical processing. The processor also determines performance guarantees for multiple settings conditioned on multiple characteristics of an application scenario for the held-out data of the taxonomy based on the underlying performance metrics. The processor further provides confidence intervals based on the performance guarantees.

Growing community of inventors

San Jose, CA, United States of America

Yunyao Li