Richard John Darden, 65North Las Vegas, NV

2014001, Jan 16, 2014

Jul 13, 2012

13/549056

Aaron K. Baughman - Silver Spring MD, US
Richard L. Darden - Leesburg VA, US
James J. Fan - Mountain Lakes NJ, US
Aditya A. Kalyanpur - Fort Lee NJ, US

INTERNATIONAL BUSINESS MACHINES CORPORATION - Armonk NY

G06K 9/00

382100

An approach that provides hierarchical and index based watermarks represented as trees is described. In one embodiment, a watermark tree is formed from feature watermarks generated from a natural language processing (NLP) stack having NLP analytics. The watermark tree represents a hierarchical relationship between each of the feature watermarks. In particular, the watermark tree defines hierarchical pointers that point out inherited watermarks that exist between the feature watermarks according to the hierarchical relationship. Further, the watermark tree includes a time stamp specifying a time that a data set content residing in a corpus was accessed.

2013034, Dec 26, 2013

Jun 26, 2012

13/533164

Aaron K. Baughman - Silver Spring MD, US
Linda M. Boyer - Ossining NY, US
Christopher F. Codella - LaGrangeville NY, US
Richard L. Darden - Leesburg VA, US
William G. Dubyak - Severna Park MD, US
Arnold Greenland - Silver Spring MD, US

INTERNATIONAL BUSINESS MACHINES CORPORATION - Armonk NY

G06F 15/173

709226

A workload associated with a task is assessed with respect to each of a plurality of computing paradigms offered by a cloud computing environment. Adaptive learning is employed by maintaining a table of Q-values corresponding to the computing paradigms and the workload is distributed according to a ratio of Q-values. The Q-values may be adjusted responsive to a performance metric and/or a value, reward, and/or decay function. The workload is then assigned to available computing paradigms to be performed with improved utilization of resources.

2019022, Jul 25, 2019

Apr 5, 2019

16/376338

- Armonk NY, US
Paul J. Chase - Fairfax VA, US
Richard Darden - Leesburg VA, US
Michael Drzewucki - Woodbridge VA, US
Edward G. Katz - Washington DC, US
Christopher Phipps - Arlington VA, US

G06F 17/27
G06F 16/33
G06F 16/332
G06F 16/93

An apparatus comprising a memory and a processor configured for semi-autonomous natural language processing domain adaptation related activities. The processor coupled to the memory and configured to identify a corpus of documents of an evaluation domain and generate a first lexicon based on the corpus of documents of the evaluation domain, and determine a threshold that indicates a sufficiency of domain adaptation of the evaluation domain based at least in part on the first lexicon. The processor is further configured to identify a corpus of documents of a client domain, generate a second lexicon based on the corpus of documents of the client domain, determine a metric associated with the corpus of documents of the client domain and the second lexicon, and determine that domain adaptation of the client domain is complete when the metric exceeds the threshold.

2019016, May 30, 2019

Nov 29, 2017

15/825742

- Armonk NY, US
Yashavant Singh - Ashburn VA, US
Palani Sakthi - Palatine IL, US
Richard Lee Darden - Leesburg VA, US

G06N 5/02
G06F 17/30

The present invention may include an embodiment to improve the performance (both response time and quality of answers) of a knowledge based service operating on a master catalog of data by dynamically building a narrowed, focused, and reduced corpus of data over which the knowledge based service operates. The embodiment may identify a corpus catalog for a knowledge base service, where the knowledge base service includes one or more documents. Then the embodiment may determine one or more subjects based on profile preferences of a user and determining the one or more documents corresponding to the determined one or more subjects based on determining the one or more subjects were updated. The embodiment may stage the determined one or more documents in a master corpus, where the master corpus is a subset of the corpus catalog and upload the master corpus to the knowledge base service.

2019002, Jan 24, 2019

Jul 24, 2017

15/657977

- ARMONK NY, US
Richard L. Darden - Leesburg VA, US
Michael Drzewucki - Woodbridge VA, US
Edward G. Katz - Washington DC, US
Christopher Phipps - Arlington VA, US

G06F 17/30
G06N 5/02

A method, computer system, and a computer program product for collecting related factoid answers into a single object is provided. The present invention may include identifying an informativeness criteria. The present invention may also include identifying a query. The present invention may then include receiving a plurality of answer terms. The present invention may then include generating a plurality of informative factoid answers. The present invention may then include identifying a plurality of relation-bearing elements. The present invention may then include grouping the plurality of informative factoid answers into a single object. The present invention may then include generating a plurality of relations from the plurality of informative factoid answers and the plurality of relation-bearing elements. The present invention may further include creating a plurality of knowledge base entries from the plurality of relations. The present invention may also include storing the plurality of knowledge entries in a knowledge base.

2019002, Jan 24, 2019

Jul 24, 2017

15/657936

- ARMONK NY, US
Richard L. Darden - Leesburg VA, US
Michael Drzewucki - Woodbridge VA, US
Edward G. Katz - Washington DC, US
Christopher Phipps - Arlington VA, US

G06N 5/02
G06F 17/30
G06N 7/00

A method, computer system, and a computer program product for converting a plurality of factoid answers into a plurality of structured relations for storage in a structured knowledge base is provided. The present invention may include receiving a query from a user. The present invention may also include generating a plurality of possible factoid answers. The present invention may then include determining a plurality of confidence scores for the plurality of possible factoid answers. The present invention may then include generating a plurality of certain factoid answers from the plurality of possible factoid answers. The present invention may then include identifying a plurality of special target items. The present invention may further include generating a plurality of structured relations for each certain factoid answer and the identified plurality of special target items. The present include may also include storing the generated plurality of structured relations into the structured knowledge base.

2018026, Sep 13, 2018

Mar 9, 2017

15/454778

- Armonk NY, US
Richard L. Darden - Leesburg VA, US
Michael Drzewucki - Woodbridge VA, US
Edward G. Katz - Washington DC, US
Christopher Phipps - Arlington VA, US
James E. Ramirez - Stephenson VA, US

G06F 17/27
G06F 17/21
G06F 17/30

Large lists of domain-specific terms are classified as a particular kind of linguistic object, e.g., lexical answer type T versus canonical answer E, based on features from a domain-specific corpus which have been found to distinguish between the linguistic objects. The distinguishing features can be identified in the corpus based on sets of the linguistic objects derived from question-and-answer pairs. A classifier can be trained using the distinguishing features, and the classification carried out using that classifier. The distinguishing features can include one or more syntactic features or one or more lexical features. The linguistic objects (the T and E training sets) can be extracted from the question-and-answer pairs automatically via text analysis if manually curated lists are not available. The classified terms can be included in a domain-specific lexicon which facilitates a deep question answering system to yield an answer to a question.

2018026, Sep 13, 2018

Jun 9, 2017

15/618910

- Armonk NY, US
Richard L. Darden - Leesburg VA, US
Michael Drzewucki - Woodbridge VA, US
Edward G. Katz - Washington DC, US
Christopher Phipps - Arlington VA, US
James E. Ramirez - Stephenson VA, US

G06F 17/27
G06F 17/30
G06F 17/21

Large lists of domain-specific terms are classified as a particular kind of linguistic object, e.g., lexical answer type T versus canonical answer E, based on features from a domain-specific corpus which have been found to distinguish between the linguistic objects. The distinguishing features can be identified in the corpus based on sets of the linguistic objects derived from question-and-answer pairs. A classifier can be trained using the distinguishing features, and the classification carried out using that classifier. The distinguishing features can include one or more syntactic features or one or more lexical features. The linguistic objects (the T and E training sets) can be extracted from the question-and-answer pairs automatically via text analysis if manually curated lists are not available. The classified terms can be included in a domain-specific lexicon which facilitates a deep question answering system to yield an answer to a question.