Xiaoqiang Luo

7398274, Jul 8, 2008

Apr 27, 2004

10/833256

Abraham Ittycheriah - Brookfield CT, US
Hongyan Jing - White Plains NY, US
Nandakishore Kambhatla - White Plains NY, US
Xiaoqiang Luo - Ardsley NY, US
Salim E. Roukos - Scarsdale NY, US

International Business Machines Corporation - Armonk NY

G06F 7/00

707100, 707102

A Bell Tree data structure is provided to model the process of chaining the mentions, from one or more documents, into entities, tracking the entire process; where the data structure is used in an entity tracking process that produces multiple results ranked by a product of probability scores.

7464024, Dec 9, 2008

Apr 16, 2004

10/826707

Xiaoqiang Luo - Ardsley NY, US
Robert Todd Ward - Croton on Hudson NY, US

International Business Machines Corporation - Armonk NY

G06F 17/27

704 9

A parser is provided that parses a Chinese text stream at the character level and builds a syntactic structure of Chinese character sequences. A character-based syntactic parse tree contains word boundaries, part-of-speech tags, and phrasal structure information. Syntactic knowledge constrains the system when it determines word boundaries. A deterministic procedure is used to convert word-based parse trees into character-based trees. Character-level tags are derived from word-level part-of-speech tags and word-boundary information is encoded with a positional tag. Word-level parts-of-speech become a constituent label in character-based trees. A maximum entropy parser is then built and tested.

8620961, Dec 31, 2013

May 5, 2008

12/115321

Abraham Ittycheriah - Brookfield CT, US
Hongyan Jing - White Plains NY, US
Nandakishore Kambhatla - White Plains NY, US
Xiaoqiang Luo - Ardsley NY, US
Salim E. Roukos - Scarsdale NY, US

International Business Machines Corporation - Armonk NY

G06F 7/00
G06F 17/30

707797

A Bell Tree data structure is provided to model the process of chaining the mentions, from one or more documents, into entities, tracking the entire process; where the data structure is used in an entity tracking process that produces multiple results ranked by a product of probability scores.

20020111793, Aug 15, 2002

Dec 14, 2000

09/737259

Xiaoqiang Luo - White Plains NY, US
Salim Roukos - Scarsdale NY, US
Robert Ward - Croton-on-Hudson NY, US

IBM Corporation

G06F017/21
G06F017/27

704/010000

An arrangement for adapting statistical parsers to new data using a mathematical transform, particularly a Markov transform. In particular, it is assumed that an initial statistical parser is available and a batch of new data is given. The initial model is mapped to a new model by a Markov matrix, each of whose rows sums to one. In the unsupervised setup, where “true” parses are missing, the transform matrix is obtained by maximizing the log likelihood of the parses of test data decoded using the model before adaptation. The proposed algorithm can be applied to supervised adaptation, as well.

20040111253, Jun 10, 2004

Dec 10, 2002

10/315537

Xiaoqiang Luo - Ardsley NY, US
Salim Roukos - Scarsdale NY, US
Min Tang - Cambridge MA, US

International Business Machines Corporation - Armonk NY

G06F017/28

704/004000

A method, computer program product, and data processing system for training a statistical parser by utilizing active learning techniques to reduce the size of the corpus of human-annotated training samples (e.g., sentences) needed is disclosed. According to a preferred embodiment of the present invention, the statistical parser under training is used to compare the grammatical structure of the samples according to the parser's current level of training. The samples are then divided into clusters, with each cluster representing samples having a similar structure as ascertained by the statistical parser. Uncertainty metrics are applied to the clustered samples to select samples from each cluster that reflect uncertainty in the statistical parser's grammatical model. These selected samples may then be annotated by a human trainer for training the statistical parser.

20130185049, Jul 18, 2013

Jan 12, 2012

13/348995

Bing Zhao - Stamford CT, US
Imed Zitouni - White Plains NY, US
Xiaoqiang Luo - Ardsley NY, US
Vittorio Castelli - Croton on Hudson NY, US

INTERNATIONAL BUSINESS MACHINES CORPORATION - Armonk NY

G06F 17/28
G06F 17/27

704 2, 704 9

A method, an apparatus and an article of manufacture for determining a dropped pronoun from a source language. The method includes collecting parallel sentences from a source and a target language, creating at least one word alignment between the parallel sentences in the source and the target language, mapping at least one pronoun from the target language sentence onto the source language sentence, computing at least one feature from the mapping, wherein the at least one feature is extracted from both the source language and the at least one pronoun projected from the target language, and using the at least one feature to train a classifier to predict position and spelling of at least one pronoun in the target language when the at least one pronoun is dropped in the source language.

20130332450, Dec 12, 2013

Jun 11, 2012

13/493659

Vittorio Castelli - Yorktown Heights NY, US
Radu Florian - Yorktown Heights NY, US
Xiaoqiang Luo - Yorktown Heights NY, US
Hema Raghavan - Yorktown Heights NY, US

International Business Machines Corporation - Armonk NY

G06F 17/30
G06F 17/28

707722, 707737, 707736, 707748, 707E17014, 707E17046

A method for automatically extracting and organizing information by a processing device from a plurality of data sources is provided. A natural language processing information extraction pipeline that includes an automatic detection of entities is applied to the data sources. Information about detected entities is identified by analyzing products of the natural language processing pipeline. Identified information is grouped into equivalence classes containing equivalent information. At least one displayable representation of the equivalence classes is created. An order in which the at least one displayable representation is displayed is computed. A combined representation of the equivalence classes that respects the order in which the displayable representation is displayed is produced.

20220253540, Aug 11, 2022

Feb 5, 2021

17/169161

- Redmond WA, US
Tianhao LU - New York City NY, US
Xiaoqiang LUO - Cos Cob CT, US
Jiashuo WANG - Mountain View CA, US
Chencheng WU - Los Altos CA, US

G06F 21/62
G06K 9/62
G06N 20/00

Techniques for securely storing and processing data for training data generation are provided. In one technique, multiple encrypted records are retrieved from a first persistent storage. For each encrypted record, that record is decrypted in memory to generate a decrypted record that comprises multiple attribute values. Then, based on the attribute values and a definition of multiple features of a machine-learned model, multiple feature values are generated and stored, along with a label, in a training instance, which is then stored in a second persistent storage. One or more machine learning techniques are used to train the machine-learned model based on training data that includes the training instances that are stored in the second persistent storage.