Patent application number | Description | Published |
20090319507 | METHODS AND APPARATUSES FOR ADAPTING A RANKING FUNCTION OF A SEARCH ENGINE FOR USE WITH A SPECIFIC DOMAIN - Methods and apparatuses are provided for adapting hierarchical structure information associated with a first ranking function tuned for use in a first domain for use in a second domain. | 12-24-2009 |
20140172899 | PROBABILITY-BASED STATE MODIFICATION FOR QUERY DIALOGUES - A device may facilitate a query dialog involving queries that successively modify a query state. However, fulfilling such queries in the context of possible query domains, query intents, and contextual meanings of query terms may be difficult. Presented herein are techniques for modifying a query state in view of a query by utilizing a set of query state modifications, each representing a modification of the query state possibly intended by the user while formulating the query (e.g., adding, substituting, or removing query terms; changing the query domain or query intent; and navigating within a hierarchy of saved query states). Upon receiving a query, an embodiment may calculate the probability of the query connoting each query state modification (e.g., using a Bayesian classifier), and parsing the query according to a query state modification having a high probability (e.g., mapping respective query terms to query slots within the current query intent). | 06-19-2014 |
20140201629 | COLLABORATIVE LEARNING THROUGH USER GENERATED KNOWLEDGE - A feedback loop is used by a central knowledge manager to obtain information from different users and deliver learned information to other users. Each user utilizes a personal assistant that learns from the user over time. The user may teach their personal assistant new knowledge through a natural user interface (NUI) and/or some other interface. For example, a combination of a natural language dialog and other non-verbal modalities of expressing intent (gestures, touch, gaze, images/videos, spoken prosody, . . . ) may be used to interact with the personal assistant. As knowledge is learned, each personal assistant sends the newly learned knowledge back to the knowledge manager. The knowledge obtained from the personal assistants is combined to form a collective intelligence. This collective intelligence is then transferred back to each of the individual personal assistants. In this way, the knowledge of one personal assistant benefits the other personal assistants through the feedback loop. | 07-17-2014 |
20140214421 | PROSODIC AND LEXICAL ADDRESSEE DETECTION - Prosodic features are used for discriminating computer-directed speech from human-directed speech. Statistics and models describing energy/intensity patterns over time, speech/pause distributions, pitch patterns, vocal effort features, and speech segment duration patterns may be used for prosodic modeling. The prosodic features for at least a portion of an utterance are monitored over a period of time to determine a shape associated with the utterance. A score may be determined to assist in classifying the current utterance as human directed or computer directed without relying on knowledge of preceding utterances or utterances following the current utterance. Outside data may be used for training lexical addressee detection systems for the H-H-C scenario. H-C training data can be obtained from a single-user H-C collection and that H-H speech can be modeled using general conversational speech. H-C and H-H language models may also be adapted using interpolation with small amounts of matched H-H-C data. | 07-31-2014 |
20140236570 | EXPLOITING THE SEMANTIC WEB FOR UNSUPERVISED SPOKEN LANGUAGE UNDERSTANDING - An unsupervised training approach for Spoken Language Understanding (SLU) systems uses the structure of content sources (e.g. semantic knowledge graphs, relational databases, . . . ) to automatically specify a semantic representation for SLU. The semantic representation is used when creating entity-relation patterns that are used to mine natural language (NL) examples (e.g. NL surface forms from the web and search query click logs). The structure of the content source (e.g. semantic graph) is enriched with the mined NL examples. The NL examples and patterns may be used to automatically train SLU systems in an unsupervised manner that covers the knowledge represented in the structured content. | 08-21-2014 |
20140236575 | EXPLOITING THE SEMANTIC WEB FOR UNSUPERVISED NATURAL LANGUAGE SEMANTIC PARSING - Structured web pages are accessed and parsed to obtain implicit annotation for natural language understanding tasks. Search queries that hit these structured web pages are automatically mined for information that is used to semantically annotate the queries. The automatically annotated queries may be used for automatically building statistical unsupervised slot filling models without using a semantic annotation guideline. For example, tags that are located on a structured web page that are associated with the search query may be used to annotate the query. The mined search queries may be filtered to create a set of queries that is in a form of a natural language query and/or remove queries that are difficult to parse. A natural language model may be trained using the resulting mined queries. Some queries may be set aside for testing and the model may be adapted using in-domain sentences that are not annotated. The models may be tested using these implicitly annotated natural-language-like queries in an unsupervised fashion. | 08-21-2014 |
20140250378 | USING HUMAN WIZARDS IN A CONVERSATIONAL UNDERSTANDING SYSTEM - A wizard control panel may be used by a human wizard to adjust the operation of a Natural Language (NL) conversational system during a real-time dialog flow. Input to the wizard control panel is detected and used to interrupt/change an automatic operation of one or more of the NL conversational system components used during the flow. For example, the wizard control panel may be used to adjust results determined by an Automated Speech Recognition (ASR) component, a Natural Language Understanding (NLU) component, a Dialog Manager (DM) component, and a Natural Language Generation (NLG) before the results are used to perform an automatic operation within the flow. A timeout may also be set such that when the timeout expires, the conversational system performs an automated operation by using the results shown in the wizard control panel (edited/not edited). | 09-04-2014 |
20140379323 | ACTIVE LEARNING USING DIFFERENT KNOWLEDGE SOURCES - Different knowledge sources are automatically accessed to identify and obtain additional data to update a conversational dialog system. One of the knowledge sources is initially selected as a seed source. Seed data from the seed source are used to identify related data in at least one other knowledge source. For example, query click logs may be accessed and searched to determine popular queries that use the seed data. A structured knowledge source may be accessed to determine related nodes to the seed data. A query click log, or some other knowledge source, may be used to determine when a node is related to the seed data. Data that is identified to be related may be used to train a language understanding model or update a schema for the SLU system. The data may be automatically annotated or manually annotated. | 12-25-2014 |
20140379326 | BUILDING CONVERSATIONAL UNDERSTANDING SYSTEMS USING A TOOLSET - Tools are provided to allow developers to enable applications for Conversational Understanding (CU) using assets from a CU service. The tools may be used to select functionality from existing domains, extend the coverage of one or more domains, as well as to create new domains in the CU service. A developer may provide example Natural Language (NL) sentences that are analyzed by the tools to assist the developer in labeling data that is used to update the models in the CU service. For example, the tools may assist a developer in identifying domains, determining intent actions, determining intent objects and determining slots from example NL sentences. After the developer tags all or a portion of the example NL sentences, the models in the CU service are automatically updated and validated. For example, validation tools may be used to determine an accuracy of the model against test data. | 12-25-2014 |
20140379353 | Environmentally aware dialog policies and response generation - Environmental conditions, along with other information, are used to adjust a response of a conversational dialog system. The environmental conditions may be used at different times within the conversational dialog system. For example, the environmental conditions can be used to adjust the dialog manager's output (e.g., the machine action). The dialog state information that is used by the dialog manager includes environmental conditions for the current turn in the dialog as well as environmental conditions for one or more past turns in the dialog. The environmental conditions can also be used after receiving the machine action to adjust the response that is provided to the user. For example, the environmental conditions may affect the machine action that is determined as well as how the action is provided to the user. The dialog manager and the response generation components in the conversational dialog system each use the available environmental conditions. | 12-25-2014 |