Abstract: To construct a classifier, a data structure correlating queries to items identified by the queries is received, where the data structure contains initial labeled queries that have been labeled with respect to predetermined classes, and unlabeled queries that have not been labeled with respect to the predetermined classes. The data structure is used to label at least some of the unlabeled queries with respect to the predetermined classes. Queries in the data structure that have been labeled with respect to the predetermined classes are used as training data to train the classifier.

Abstract: The present invention uses a natural language understanding system that is currently being trained to assist in annotating training data for training that natural language understanding system. Unannotated training data is provided to the system and the system proposes annotations to the training data. The user is offered an opportunity to confirm or correct the proposed annotations, and the system is trained with the corrected or verified annotations.

Abstract: A method and system to generate a grammar adapted for use by a speech recognizer includes receiving a representation of an alphanumeric expression. For instance, the representation can take the form of a regular expression or a mask. The grammar is generated based on the representation.

Abstract: A computer-implemented method is disclosed for providing a directory assistance service. The method includes generating an indexing file that is a representation of information associated with a collection of listings stored in an index. The indexing file is utilized as a basis for ranking listings in an index based on the strength of association with a query. Based at least in part on the ranking, an output is provided and is indicative of listings in the index that are likely correspond to the query. At least one particular listing in the index is excluded from the output without there ever being a comparison of features in the query with features in the one particular listing.

Abstract: The present invention uses a natural language understanding system that is currently being trained to assist in annotating training data for training that natural language understanding system. Unannotated training data is provided to the system and the system proposes annotations to the training data. The user is offered an opportunity to confirm or correct the proposed annotations, and the system is trained with the corrected or verified annotations.

Abstract: Described is a technology by which a maximum entropy model used for classification is trained with a significantly lesser amount of training data than is normally used in training other maximum entropy models, yet provides similar accuracy to the others. The maximum entropy model is initially parameterized with parameter values determined from weights obtained by training a vector space model or an n-gram model. The weights may be scaled into the initial parameter values by determining a scaling factor. Gaussian mean values may also be determined, and used for regularization in training the maximum entropy model. Scaling may also be applied to the Gaussian mean values. After initial parameterization, training comprises using training data to iteratively adjust the initial parameters into adjusted parameters until convergence is determined.

Abstract: A method for authoring a grammar for use in a language processing application is provided. The method includes receiving at least one grammar configuration parameter relating to how to configure a grammar and creating the grammar based on the at least one grammar configuration parameter.

Abstract: A voice search system has a speech recognizer, a search component, and a dialog manager. A confidence measure generator receives speech recognition features from the speech recognizer, search features from the search component, and dialog features from the dialog manager, and calculates an overall confidence measure for voice search results based upon the features received. The invention can be extended to include the generation of additional features, based on those received from the individual components of the voice search system.

Abstract: A directory assistance system includes a directory database and a search engine. The search engine is configured to search the directory database for a first set of residential listings based on at least one first search term. A second search term is received that is related to a cohabitant of the listing to be found. At least one search result is selected that satisfies the second search term.

Abstract: A database having listings rather than long documents is searched using a term frequency-inverse document frequency (Tf/Idf) algorithm.

Abstract: A structured database is used for webpage information extraction, and in particular, to obtain training data from the webpage for training a statistical model. The structured database has a plurality of entries, wherein each entry comprises a plurality of fields. One of the fields comprises a URL (uniform resource locater), while another field comprises information at least similar to other information to be located in a webpage associated with the URL. For at least some of the entries in the structured database, a web page associated with the URL is retrieved. The webpage is analyzed and if information is found in the webpage similar to the information in the structured database, the webpage is identified as being suitable to be considered as a training sample.

Abstract: A novel system integrates speech recognition and semantic classification, so that acoustic scores in a speech recognizer that accepts spoken utterances may be taken into account when training both language models and semantic classification models. For example, a joint association score may be defined that is indicative of a correspondence of a semantic class and a word sequence for an acoustic signal. The joint association score may incorporate parameters such as weighting parameters for signal-to-class modeling of the acoustic signal, language model parameters and scores, and acoustic model parameters and scores. The parameters may be revised to raise the joint association score of a target word sequence with a target semantic class relative to the joint association score of a competitor word sequence with the target semantic class. The parameters may be designed so that the semantic classification errors in the training data are minimized.

Abstract: A computer-implemented method is disclosed for providing a directory assistance service. The method includes generating an indexing file that is a representation of information associated with a collection of listings stored in an index. The indexing file is utilized as a basis for ranking listings in an index based on the strength of association with a query. Based at least in part on the ranking, an output is provided and is indicative of listings in the index that are likely correspond to the query. At least one particular listing in the index is excluded from the output without there ever being a comparison of features in the query with features in the one particular listing.

Abstract: An answering machine detection module is used to determine whether a call recipient is an actual person or an answering machine. The answering machine detection module includes a speech recognizer and a call analysis module. The speech recognizer receives an audible response of the call recipient to a call. The speech recognizer processes the audible response and provides an output indicative of recognized speech. The call analysis module processes the output of the speech recognizer to generate an output indicative of whether the call recipient is a person or an answering machine.

Abstract: A method for creating a language model from a task-independent corpus is provided. In one embodiment, a task dependent unified language model is created. The unified language model includes a plurality of context-free grammars having non-terminals and a hybrid N-gram model having at least some of the same non-terminals embedded therein.

Abstract: A training system for a speech recognition application is disclosed. In embodiments described, the training system is used to train a classification model or language model. The classification model is trained using an adaptive language model generated by an iterative training process. In embodiments described, the training data is recognized by the speech recognition component and the recognized text is used to create the adaptive language model which is used for speech recognition in a following training iteration.

Abstract: A method of forming a shareable filler model (shareable model for garbage words) from a word n-gram model is provided. The word n-gram model is converted into a probabilistic context free grammar (PCFG). The PCFG is modified into a substantially application-independent PCFG, which constitutes the shareable filler model.

Abstract: A conditional model is used in spoken language understanding. One such model is a conditional random field model.

Abstract: To provide application developers with the ability to easily form customized grammars, grammar extensions are provided that allow application developers to selectively include portions of grammar templates and to easily combine grammar elements to form new grammar structures.

Abstract: A method for creating a language model from a task-independent corpus is provided. In one embodiment, a task dependent unified language model is created. The unified language model includes a plurality of context-free grammars having non-terminals and a hybrid N-gram model having at least some of the same non-terminals embedded therein.