Abstract: The present invention relates to a method and apparatus for exploiting human feedback in an intelligent automated assistant. One embodiment of a method for conducting an interaction with a human user includes inferring an intent from data entered by the human user, formulating a response in accordance with the intent, receiving feedback from a human advisor in response to at least one of the inferring and the formulating, wherein the human advisor is a person other than the human user, and adapting at least one model used in at least one of the inferring and the formulating, wherein the adapting is based on the feedback.

Abstract: The present invention relates to a method and apparatus for tailoring the output of an intelligent automated assistant. One embodiment of a method for conducting an interaction with a human user includes collecting data about the user using a multimodal set of sensors positioned in a vicinity of the user, making a set of inferences about the user in accordance with the data, and tailoring an output to be delivered to the user in accordance with the set of inferences.

Abstract: The invention relates to a system and method for gathering data for use in a spoken dialog system. An aspect of the invention is generally referred to as an automated hidden human that performs data collection automatically at the beginning of a conversation with a user in a spoken dialog system. The method comprises presenting an initial prompt to a user, recognizing a received user utterance using an automatic speech recognition engine and classifying the recognized user utterance using a spoken language understanding module. If the recognized user utterance is not understood or classifiable to a predetermined acceptance threshold, then the method re-prompts the user. If the recognized user utterance is not classifiable to a predetermined rejection threshold, then the method transfers the user to a human as this may imply a task-specific utterance. The received and classified user utterance is then used for training the spoken dialog system.

Abstract: An apparatus and a method are provided for building a spoken language understanding model. Labeled data may be obtained for a target application. A new classification model may be formed for use with the target application by using the labeled data for adaptation of an existing classification model. In some implementations, the existing classification model may be used to determine the most informative examples to label.

Abstract: Combined active and semi-supervised learning to reduce an amount of manual labeling when training a spoken language understanding model classifier. The classifier may be trained with human-labeled utterance data. Ones of a group of unselected utterance data may be selected for manual labeling via active learning. The classifier may be changed, via semi-supervised learning, based on the selected ones of the unselected utterance data.

Abstract: An apparatus and a method are provided for building a spoken language understanding model. Labeled data may be obtained for a target application. A new classification model may be formed for use with the target application by using the labeled data for adaptation of an existing classification model. In some implementations, the existing classification model may be used to determine the most informative examples to label.

Abstract: Word lattices that are generated by an automatic speech recognition system are used to generate a modified word lattice that is usable by a spoken language understanding module. In one embodiment, the spoken language understanding module determines a set of salient phrases by calculating an intersection of the modified word lattice, which is optionally preprocessed, and a finite state machine that includes a plurality of salient grammar fragments.

Abstract: A spoken language understanding method and system are provided. The method includes classifying a set of labeled candidate utterances based on a previously trained classifier, generating classification types for each candidate utterance, receiving confidence scores for the classification types from the trained classifier, sorting the classified utterances based on an analysis of the confidence score of each candidate utterance compared to a respective label of the candidate utterance, and rechecking candidate utterances according to the analysis. The system includes modules configured to control a processor in the system to perform the steps of the method.

Abstract: A method of generating a natural language model for use in a spoken dialog system is disclosed. The method comprises using sample utterances and creating a number of hand crafted rules for each call-type defined in a labeling guide. A first NLU model is generated and tested using the hand crafted rules and sample utterances. A second NLU model is built using the sample utterances as new training data and using the hand crafted rules. The second NLU model is tested for performance using a first batch of labeled data. A series of NLU models are built by adding a previous batch of labeled data to training data and using a new batch of labeling data as test data to generate the series of NLU models with training data that increases constantly. If not all the labeling data is received, the method comprises repeating the step of building a series of NLU models until all labeling data is received.

Abstract: Systems and methods for annotating speech data. The present invention reduces the time required to annotate speech data by selecting utterances for annotation that will be of greatest benefit. A selection module uses speech models, including speech recognition models and spoken language understanding models, to identify utterances that should be annotated based on criteria such as confidence scores generated by the models. These utterances are placed in an annotation list along with a type of annotation to be performed for the utterances and an order in which the annotation should proceed. The utterances in the annotation list can be annotated for speech recognition purposes, spoken language understanding purposes, labeling purposes, etc. The selection module can also select utterances for annotation based on previously annotated speech data and deficiencies in the various models.

Abstract: A method is disclosed for generating labeled utterances from human-human utterances for use in training a semantic classification model for a spoken dialog system. The method comprises augmenting received human-human utterances with data that relates to call-type gaps in the human-human utterances, augmenting the received human-human utterances by placing at least one word in the human-human utterances that improves the training ability of the utterances according to the conversation patterns of the spoken dialog system, clausifying the human-human utterances, labeling the clausified and augmented human-human utterances and building the semantic classification model for the spoken dialog system using the labeled utterances.

Abstract: A system and method for exploiting unlabeled utterances in the augmentation of a classifier model is disclosed. In one embodiment, a classifier is initially trained using a labeled set of utterances. Another set of utterances is then selected from an available set of unlabeled utterances. In one embodiment, this selection process can be based on a confidence score threshold. The trained classifier is then augmented using the selected set of unlabeled utterances.

Abstract: Disclosed is a system and method of training a spoken language understanding module. Such a module may be utilized in a spoken dialog system. The method of training a spoken language understanding module comprises training acoustic and language models using a small set of transcribed data St, recognizing utterances in a set Su that are candidates for transcription using the acoustic and language models, computing confidence scores of the utterances, selecting k utterances that have the smallest confidence scores from Su and transcribing them into a new set Si, redefining St as the union of St and Si, redefining Su as Su minus Si, and returning to the step of training acoustic and language models if word accuracy has not converged.

Abstract: An apparatus and a method are provided for using semantic role labeling for spoken language understanding. A received utterance semantically parsed by semantic role labeling. A predicate or at least one argument is extracted from the semantically parsed utterance. An intent is estimated based on the predicate or the at least one argument. In another aspect, a method is provided for training a spoken language dialog system that uses semantic role labeling. An expert is provided with a group of predicate/argument pairs. Ones of the predicate/argument pairs are selected as intents. Ones of the arguments are selected as named entities. Mappings from the arguments to frame slots are designed.

Abstract: A system, method and computer-readable medium provide a multitask learning method for intent or call-type classification in a spoken language understanding system. Multitask learning aims at training tasks in parallel while using a shared representation. A computing device automatically re-uses the existing labeled data from various applications, which are similar but may have different call-types, intents or intent distributions to improve the performance. An automated intent mapping algorithm operates across applications. In one aspect, active learning is employed to selectively sample the data to be re-used.

Abstract: A method of generating a natural language model for use in a spoken dialog system is disclosed. The method comprises using sample utterances and creating a number of hand crafted rules for each call-type defined in a labeling guide. A first NLU model is generated and tested using the hand crafted rules and sample utterances. A second NLU model is built using the sample utterances as new training data and using the hand crafted rules. The second NLU model is tested for performance using a first batch of labeled data. A series of NLU models are built by adding a previous batch of labeled data to training data and using a new batch of labeling data as test data to generate the series of NLU models with training data that increases constantly. If not all the labeling data is received, the method comprises repeating the step of building a series of NLU models until all labeling data is received.

Abstract: A system, method and computer-readable medium provide a multitask learning method for intent or call-type classification in a spoken language understanding system. Multitask learning aims at training tasks in parallel while using a shared representation. A computing device automatically re-uses the existing labeled data from various applications, which are similar but may have different call-types, intents or intent distributions to improve the performance. An automated intent mapping algorithm operates across applications. In one aspect, active learning is employed to selectively sample the data to be re-used.

Abstract: A method of generating a natural language model for use in a spoken dialog system is disclosed. The method comprises using sample utterances and creating a number of hand crafted rules for each call-type defined in a labeling guide. A first NLU model is generated and tested using the hand crafted rules and sample utterances. A second NLU model is built using the sample utterances as new training data and using the hand crafted rules. The second NLU model is tested for performance using a first batch of labeled data. A series of NLU models are built by adding a previous batch of labeled data to training data and using a new batch of labeling data as test data to generate the series of NLU models with training data that increases constantly. If not all the labeling data is received, the method comprises repeating the step of building a series of NLU models until all labeling data is received.

Abstract: A spoken language understanding method and system are provided. The method includes classifying a set of labeled candidate utterances based on a previously trained classifier, generating classification types for each candidate utterance, receiving confidence scores for the classification types from the trained classifier, sorting the classified utterances based on an analysis of the confidence score of each candidate utterance compared to a respective label of the candidate utterance, and rechecking candidate utterances according to the analysis. The system includes modules configured to control a processor in the system to perform the steps of the method.

Abstract: Word lattices that are generated by an automatic speech recognition system are used to generate a modified word lattice that is usable by a spoken language understanding module. In one embodiment, the spoken language understanding module determines a set of salient phrases by calculating an intersection of the modified word lattice, which is optionally preprocessed, and a finite state machine that includes a plurality of salient grammar fragments.