Abstract: A computer implemented method for generating a report that includes latent information, comprising receiving an input data stream that includes latent information, performing one of normalization, validation, and extraction of the input data stream, processing the input data stream to identify latent information within the data stream that is required for generation of a particular report, wherein said processing of the input data stream to identify latent information comprises of identifying a relevant portion of the input data stream, bounding the relevant portion of the input data stream, classifying and normalizing the bounded data, activating a relevant report template based on said identified latent information, populating said template with template-specified data, and processing the template-specified data to generate a report.

Abstract: An interactive response system mixes HSR subsystems with ASR subsystems to facilitate overall capability of voice user interfaces. The system permits imperfect ASR subsystems to nonetheless relieve burden on HSR subsystems. An ASR proxy is used to implement an IVR system, and the proxy dynamically determines how many ASR and HSR subsystems are to perform recognition for any particular utterance, based on factors such as confidence thresholds of the ASRs and availability of human resources for HSRs.

Abstract: A computer implemented method for generating a report that includes latent information, comprising receiving an input data stream that includes latent information, performing one of normalization, validation, and extraction of the input data stream, processing the input data stream to identify latent information within the data stream that is required for generation of a particular report, wherein said processing of the input data stream to identify latent information comprises of identifying a relevant portion of the input data stream, bounding the relevant portion of the input data stream, classifying and normalizing the bounded data, activating a relevant report template based on said identified latent information, populating said template with template-specified data, and processing the template-specified data to generate a report.

Abstract: A computer implemented method for generating a report that includes latent information, comprising receiving an input data stream that includes latent information, performing one of normalization, validation, and extraction of the input data stream, processing the input data stream to identify latent information within the data stream that is required for generation of a particular report, wherein said processing of the input data stream to identify latent information comprises of identifying a relevant portion of the input data stream, bounding the relevant portion of the input data stream, classifying and normalizing the bounded data, activating a relevant report template based on said identified latent information, populating said template with template-specified data, and processing the template-specified data to generate a report.

Abstract: The invention involves the loading and unloading of dynamic section grammars and language models in a speech recognition system. The values of the sections of the structured document are either determined in advance from a collection of documents of the same domain, document type, and speaker; or collected incrementally from documents of the same domain, document type, and speaker; or added incrementally to an already existing set of values. Speech recognition in the context of the given field is constrained to the contents of these dynamic values. If speech recognition fails or produces a poor match within this grammar or section language model, speech recognition against a larger, more general vocabulary that is not constrained to the given section is performed.

Abstract: The invention involves the loading and unloading of dynamic section grammars and language models in a speech recognition system. The values of the sections of the structured document are either determined in advance from a collection of documents of the same domain, document type, and speaker; or collected incrementally from documents of the same domain, document type, and speaker; or added incrementally to an already existing set of values. Speech recognition in the context of the given field is constrained to the contents of these dynamic values. If speech recognition fails or produces a poor match within this grammar or section language model, speech recognition against a larger, more general vocabulary that is not constrained to the given section is performed.

Abstract: A computer implemented method for generating a report that includes latent information, comprising receiving an input data stream that includes latent information, performing one of normalization, validation, and extraction of the input data stream, processing the input data stream to identify latent information within the data stream that is required for generation of a particular report, wherein said processing of the input data stream to identify latent information comprises of identifying a relevant portion of the input data stream, bounding the relevant portion of the input data stream, classifying and normalizing the bounded data, activating a relevant report template based on said identified latent information, populating said template with template-specified data, and processing the template-specified data to generate a report.

Abstract: A computer implemented method for generating a report that includes latent information, comprising receiving an input data stream that includes latent information, performing one of normalization, validation, and extraction of the input data stream, processing the input data stream to identify latent information within the data stream that is required for generation of a particular report, wherein said processing of the input data stream to identify latent information comprises of identifying a relevant portion of the input data stream, bounding the relevant portion of the input data stream, classifying and normalizing the bounded data, activating a relevant report template based on said identified latent information, populating said template with template-specified data, and processing the template-specified data to generate a report.

Abstract: A computer implemented method for generating a report that includes latent information, comprising receiving an input data stream that includes latent information, performing one of normalization, validation, and extraction of the input data stream, processing the input data stream to identify latent information within the data stream that is required for generation of a particular report, wherein said processing of the input data stream to identify latent information comprises of identifying a relevant portion of the input data stream, bounding the relevant portion of the input data stream, classifying and normalizing the bounded data, activating a relevant report template based on said identified latent information, populating said template with template-specified data, and processing the template-specified data to generate a report.

Abstract: The disclosed invention includes an apparatus, system and method for developing tools to explore, organize, structure, extract, and mine natural language text. The system contains three sub-systems: a run-time engine, a development environment, and a feedback system. The invention also includes a system and method for improving the quality of information extraction applications consisting of an ensemble of per-user, adaptive, on-line machine-learning classifiers that adapt to document content and judgments of users by continuously incorporating feedback from information extraction results and corrections that users apply to these results. At least one of the machine-learning classifier also provides explanations or justifications for classification decisions in the form of rules; other machine-learning classifiers may provide feedback in the form of supporting instances or patterns.

Abstract: A system and method for filtering documents to determine section boundaries between dictated and non-dictated text. The system and method identifies portions of a text report that correspond to an original dictation and, correspondingly, those portions that are not part of the original dictation. The system and method include comparing tokenized and normalized forms of the original dictation and the final report, determining mismatches between the two forms, and applying machine-learning techniques to identify document headers, footers, page turns, macros, and lists automatically and accurately.

Abstract: A system and method for filtering documents to determine section boundaries between dictated and non-dictated text. The system and method identifies portions of a text report that correspond to an original dictation and, correspondingly, those portions that are not part of the original dictation. The system and method include comparing tokenized and normalized forms of the original dictation and the final report, determining mismatches between the two forms, and applying machine-learning techniques to identify document headers, footers, page turns, macros, and lists automatically and accurately.

Abstract: One embodiment generally pertains to a method of prediction. The method includes generating a set of affixes from a selected input sequence and comparing the set of affixes with a predictive set of affixes. The method also includes selecting an affix from the predictive set of affixes. The invention uses various input data sets and allows the ability to perfectly render the original data set and the minimal size of the predictive set of affixes.

Abstract: The present invention pertains to a system and method for the tokenization of text. The featurizer may be configured to receive input text and convert the input text into tokens. According to one aspect of the invention, the tokens may include only one type of character, the characters selected from the group consisting of letters, numbers, and punctuation. The tokenizer may also include a classifier. The classifier may be configured to receive the tokens from the featurizer. Furthermore, the classifier may be configured to analyze the tokens received from the featurizer to determine if the tokens may be input into a predetermined classification model using a preclassifier. If one of the tokens passes the preclassifier, then the token is classified using the predetermined classification model. Additionally, according to a first aspect of the invention, the tokenizer may also include a finalizer. The finalizer may be configured to receive the tokens and may be configured to produce a final output.

Abstract: The disclosed invention includes an apparatus, system and method for developing tools to explore, organize, structure, extract, and mine natural language text. The system contains three sub-systems: a run-time engine, a development environment, and a feedback system. The invention also includes a system and method for improving the quality of information extraction applications consisting of an ensemble of per-user, adaptive, on-line machine-learning classifiers that adapt to document content and judgments of users by continuously incorporating feedback from information extraction results and corrections that users apply to these results. At least one of the machine-learning classifier also provides explanations or justifications for classification decisions in the form of rules; other machine-learning classifiers may provide feedback in the form of supporting instances or patterns.

Abstract: The present invention relates generally to a system and method for categorization of strings of words. More specifically, the present invention relates to a system and method for normalizing a string of words for use in a system for categorization of words in a predetermined categorization scheme. A method for adaptive categorization of words in a predetermined categorization scheme may include receiving a string of text, tagging the string of text, and normalizing the string of text. Normalization may be performed with a three-stage algorithm including a literal match processing stage, an approximation match processing stage, and a nearest neighbor match processing stage. The normalized string of text can be compared to a number of sequences of text in the predetermined categorization scheme.

Abstract: A system and method for facilitating the processing and the use of documents by providing a system for categorizing document section headings under a set of canonical section headings. In the method for categorizing section headings, there may be a process of training a database and matching methods to categorize different but equivalent document section headings under canonical headings and categories. Once trained, the system may match and categorize the document sections with little to no supervision of the categorization for large sets of documents.

Abstract: A system and method is disclosed for Report Confidence Modeling (RCM) including automatic adaptive classification of ASR output documents to determine the most efficient document edit workflow to convert dictation into finished output. The RCM according to the present invention may include a mechanism to predict recognition accuracy of a document generated by an ASR engine. Predicted accuracy of the document allows an ASR application to sort recognized documents based on their estimated accuracy or quality and route them appropriately for further processing, editing and/or formatting.

Abstract: We have discovered a system and method for improving the quality of information extraction applications consisting of an ensemble of per-user, adaptive, on-line machine-learning classifiers that adapt to document content and judgments of users by continuously incorporating feedback from information extraction results and corrections that users apply to these results. The satellite classifier ensemble uses only the immediately available features for classifier improvement and it is independent of the complex cascade of earlier decisions leading to the final information extraction result. The machine-learning classifiers may also provide explanations or justifications for classification decisions in the form of rules, other machine-learning classifiers may provide feedback in the form of supporting instances or patterns.

Abstract: A method for adaptive automatic error and mismatch correction is disclosed for use with a system having an automatic error and mismatch correction learning module, an automatic error and mismatch correction model, and a classifier module. The learning module operates by receiving pairs of documents, identifying and selecting effective candidate errors and mismatches, and generating classifiers corresponding to these selected errors and mismatches. The correction model operates by receiving a string of interpreted speech into the automatic error and mismatch correction module, identifying target tokens in the string of interpreted speech, creating a set of classifier features according to requirements of the automatic error and mismatch correction model, comparing the target tokens against the classifier features to detect errors and mismatches in the string of interpreted speech, and modifying the string of interpreted speech based upon the classifier features.