Abstract: A method of grammar learning from a corpus comprises, for the other non-context words, generating frequency vectors for each non-context token in a corpus based upon counted occurrences of a predetermined relationship of the non-context tokens to identified context tokens. Clusters are grown from the frequency vectors according to a lexical correlation among the non-context tokens.

Abstract: The invention concerns a method of generating morphemes for speech recognition and understanding. The method may include receiving training speech, selecting candidate sub-morphemes from the training speech, selecting salient sub-morphemes from the candidate sub-morphemes based on salience measurements, and clustering the salient sub-morphemes based on semantic and syntactic similarities into morphemes. The morphemes may be acoustic and/or non-acoustic. The sub-morphemes may represent any sub-unit of communication including phones, phone-phrases, grammars, diphones, words, gestures, tablet strokes, body movements, mouse clicks, etc. The training speech may be verbal, non-verbal, a combination of verbal and non-verbal, or multimodal.

Abstract: A method of rapidly training an automatic speech recognizer as part of a spoken dialog system for an enterprise includes extracting information from enterprise emails, web site content, and/or speech or data records of interactions between customers and the enterprise. The method comprises extracting the relevant data to develop a domain-specific language model, generating an acoustic model from non-domain-specific data, combining the domain-specific language model with the non-domain-specific acoustic model to initially deploy the spoken dialog service, and adapting the language models as task-specific data becomes available.

Abstract: Systems and methods for translating one language to another language. A consensus translation system directs a transcription or other input to be translated by other translation systems. The outputs of those translation systems are aligned and the aligned translations are divided into segments. Each segment includes a segment translation from each of the translation outputs. The consensus translation of the transcription is constructed by selecting the majority segment translation from each segment. When there is no clear majority segment translation, the majority segment translation is selected at random or is aided by another selection criteria such as a language model.

Abstract: A method of partitioning a data set in which certain elements of the data set are first identified as robust discriminator data elements. For the other non-discriminator data elements, an embodiment of the invention counts occurrences of a predetermined relationship between each non-discriminator data element and the identified robust discriminator data elements, and maps the counted occurrences onto vectors a multi-dimensional frequency space. Finally, an embodiment forms the frequency vectors into clusters according to a distance or adjacency metric, where each cluster represents a different contextual class of meaningful attributes. The data set is thereby partitioned into an arbitrary number of clusters according to the discovered relationships between the non-discriminator data elements and the robust discriminator data elements so that all of the non-discriminator data elements located in the same cluster possess similar attributes.

Abstract: A method iteratively integrates clustering techniques with phrase acquisition techniques to build complex linguistic models from a corpus. A set of features is initialized by the corpus. Thereafter, the method determines, according to a predetermined cost function, to process the features by one of phrase clustering processing or phrase grammar learning processing. If phrase clustering processing is performed, the method processes an interstitial set of features comprising both the old features and newly established clusters by phrase grammar learning processing. The features obtained as an output of phrase grammar learning is re-indexed as a set of features for a subsequent iteration. The method may be repeated over several iterations to build a hierarchical linguistic model.

Abstract: In a method of learning grammar from a corpus, context words are identified from a corpus. For the other non-context words, the method counts the occurrence of predetermined relationships which the context words, and maps the counted occurrences to a multidimensional frequency space. Clusters are grown from the frequency vectors. The clusters represent classes of words; words in the same cluster possess the same lexical significancy and provide an indicator of grammatical structure.

Abstract: Quick-coupling device for attaching a tool (2) to an excavator comprising at least one main working arm (1); this device comprises a main body (3) provided with two side walls (306) each connected at the rear to this working arm (1) by a pin (401) housed in holes (301) in these walls (306) to allow it to be rotated relative to the said arm (1) by the movement of excavator levers (5) connected to the body (3) by a pin (40) housed in holes (302) in these walls (306) and at the front to upper walls (205) of this tool (2) by second pins (7) for locking them onto this tool (2); and these second pins (7) are able to extend out of these side walls (306) and be housed in holes (204) formed in these upper walls (205) of the tool (2) under the action of control means (8) mounted in this body (3) for automatically inserting and removing them into and from these holes (204), these upper walls (205) being provided with rear hook means (203) for attaching the tool (2) to pins (4).

Abstract: In a method of learning grammar from a corpus, context words are identified from a corpus. For the other non-context words, the method counts the occurrence of predetermined relationships which the context words, and maps the counted occurrences to a multidimensional frequency space. Clusters are grown from the frequency vectors. The clusters represent classes of words; words in the same cluster possess the same lexical significancy and provide an indicator of grammatical structure.

Abstract: A method and apparatus are provided for automatically acquiring grammar fragments for recognizing and understanding fluently spoken language. Grammar fragments representing a set of syntactically and semantically similar phrases may be generated using three probability distributions: of succeeding words, of preceding words, and of associated call-types. The similarity between phrases may be measured by applying Kullback-Leibler distance to these three probability distributions. Phrases being close in all three distances may be clustered into a grammar fragment.

Abstract: This invention is directed to the selection of superwords based on a criterion relevant to speech recognition and understanding. Superwords are used to refer to those word combinations which are so often spoken that are recognized or should have models for such combinations reflected in its grammar. The selected superwords are placed in a lexicon is then used by a speech recognizer to improve recognition of input speech utterances for the proper routing of a user's task objectives.

Abstract: This invention is directed to the automatic selection and generation of superwords based on a criterion relevant to speech recognition. Superwords are used to refer to those word combinations which are so often spoken that they can be recognized by a recognition device as being a single word.