Abstract: A dialog system for use in a multi-user, multi-domain environment. The dialog system understands user requests when multiple users are interacting with each other as well as the dialog system. The dialog system uses multi-human conversational context to improve domain detection. Using interactions between multiple users allows the dialog system to better interpret machine directed conversational inputs in multi-user conversational systems. The dialog system employs topic segmentation to chunk conversations for determining context boundaries. Using general topic segmentation methods, as well as the specific domain detector trained with conversational inputs collected by a single user system, allows the dialog system to better determine the relevant context. The use of conversational context helps reduce the domain detection error rate, especially in certain domains, and allows for better interactions with users when the machine addressed turns are not recognized or are ambiguous.

Abstract: Natural language query translation may be provided. A statistical model may be trained to detect domains according to a plurality of query click log data. Upon receiving a natural language query, the statistical model may be used to translate the natural language query into an action. The action may then be performed and at least one result associated with performing the action may be provided.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing word sequences using neural networks. One of the methods includes receiving a first sequence of words arranged according to a first order; and for each word in the first sequence, beginning with a first word in the first order: determining a topic vector that is associated with the word; generating a combined input from the word and the topic vector, and processing the combined input through one or more sequence modeling layers to generate a sequence modeling output for the word; and processing one or more of the sequence modeling outputs through an output layer to generate a neural network output for the first sequence of words.

Abstract: A relation detection model training solution. The relation detection model training solution mines freely available resources from the World Wide Web to train a relationship detection model for use during linguistic processing. The relation detection model training system searches the web for pairs of entities extracted from a knowledge graph that are connected by a specific relation. Performance is enhanced by clipping search snippets to extract patterns that connect the two entities in a dependency tree and refining the annotations of the relations according to other related entities in the knowledge graph. The relation detection model training solution scales to other domains and languages, pushing the burden from natural language semantic parsing to knowledge base population. The relation detection model training solution exhibits performance comparable to supervised solutions, which require design, collection, and manual labeling of natural language data.

Abstract: Natural language query translation may be provided. A statistical model may be trained to detect domains according to a plurality of query click log data. Upon receiving a natural language query, the statistical model may be used to translate the natural language query into an action. The action may then be performed and at least one result associated with performing the action may be provided.

Abstract: Location-based conversational understanding may be provided. Upon receiving a query from a user, an environmental context associated with the query may be generated. The query may be interpreted according to the environmental context. The interpreted query may be executed and at least one result associated with the query may be provided to the user.

Abstract: An augmented conversational understanding agent may be provided. Upon receiving, by an agent, at least one natural language phrase from a user, a context associated with the at least one natural language phrase may be identified. The natural language phrase may be associated, for example, with a conversation between the user and a second user. An agent action associated with the identified context may be performed according to the at least one natural language phrase and 201 a result associated with performing the action may be displayed.

Abstract: Identification of user intents may be provided. A plurality of network applications may be identified, and an ontology associated with each of the plurality of applications may be defined. If a phrase received from a user is associated with at least one of the defined ontologies, an action associated with the network application may be executed.

Abstract: Personalization of user interactions may be provided. Upon receiving a phrase from a user, a plurality of semantic concepts associated with the user may be loaded. If the phrase is determined to comprise at least one of the plurality of semantic concepts associated with the user, a first action may be performed according to the phrase. If the phrase is determined not to comprise at least one of the plurality of semantic concepts associated with the user, a second action may be performed according to the phrase.

Abstract: Identification of user intents may be provided. A plurality of network applications may be identified, and an ontology associated with each of the plurality of applications may be defined. If a phrase received from a user is associated with at least one of the defined ontologies, an action associated with the network application may be executed.

Abstract: An augmented conversational understanding agent may be provided. Upon receiving, by an agent, at least one natural language phrase from a user, a context associated with the at least one natural language phrase may be identified. The natural language phrase may be associated, for example, with a conversation between the user and a second user. An agent action associated with the identified context may be performed according to the at least one natural language phrase and a result associated with performing the action may be displayed, wherein the agent action comprises providing a list of movies, a list of night clubs, a search for restaurants, or other action suggestions.

Abstract: Techniques are described herein that are capable of suggesting intent frame(s) for user request(s). For instance, the intent frame(s) may be suggested to elicit a request from a user. An intent frame is a natural language phrase (e.g., a sentence) that includes at least one carrier phrase and at least one slot. A slot in an intent frame is a placeholder that is identified as being replaceable by one or more words that identify an entity and/or an action to indicate an intent of the user. A carrier phrase in an intent frame includes one or more words that suggest a type of entity and/or action that is to be identified by the one or more words that may replace the corresponding slot. In accordance with these techniques, the intent frame(s) are suggested in response to determining that natural language functionality of a processing system is activated.

Abstract: Techniques are described herein that are capable of suggesting intent frame(s) for user request(s). For instance, the intent frame(s) may be suggested to elicit a request from a user. An intent frame is a natural language phrase (e.g., a sentence) that includes at least one carrier phrase and at least one slot. A slot in an intent frame is a placeholder that is identified as being replaceable by one or more words that identify an entity and/or an action to indicate an intent of the user. A carrier phrase in an intent frame includes one or more words that suggest a type of entity and/or action that is to be identified by the one or more words that may replace the corresponding slot. In accordance with these techniques, the intent frame(s) are suggested in response to determining that natural language functionality of a processing system is activated.

Abstract: Sentence simplification may be provided. A spoken phrase may be received and converted to a text phrase. An intent associated with the text phrase may be identified. The text phrase may then be reformatted according to the identified intent and a task may be performed according to the reformatted text phrase.

Abstract: Techniques are described herein that are capable of satisfying specified intent(s) based on multimodal request(s). A multimodal request is a request that includes at least one request of a first type and at least one request of a second type that is different from the first type. Example types of request include but are not limited to a speech request, a text command, a tactile command, and a visual command. A determination is made that one or more entities in visual content are selected in accordance with an explicit scoping command from a user. In response, speech understanding functionality is automatically activated, and audio signals are automatically monitored for speech requests from the user to be processed using the speech understanding functionality.

Abstract: Sentence simplification may be provided. A spoken phrase may be received and converted to a text phrase. An intent associated with the text phrase may be identified. The text phrase may then be reformatted according to the identified intent and a task may be performed according to the reformatted text phrase.

Abstract: A model-based approach for on-screen item selection and disambiguation is provided. An utterance may be received by a computing device in response to a display of a list of items for selection on a display screen. A disambiguation model may then be applied to the utterance. The disambiguation model may be utilized to determine whether the utterance is directed to at least one of the list of displayed items, extract referential features from the utterance and identify an item from the list corresponding to the utterance, based on the extracted referential features. The computing device may then perform an action which includes selecting the identified item associated with utterance.

Abstract: Location-based conversational understanding may be provided. Upon receiving a query from a user, an environmental context associated with the query may be generated. The query may be interpreted according to the environmental context. The interpreted query may be executed and at least one result associated with the query may be provided to the user.

Abstract: A user interaction activation may be provided. A plurality of signals received from a user may be evaluated to determine whether the plurality of signals are associated with a visual display. If so, the plurality of signals may be translated into an agent action and a context associated with the visual display may be retrieved. The agent action may be performed according to the retrieved context and a result associated with the performed agent action may be displayed to the user.

Abstract: Techniques are described herein that are capable of suggesting intent frame(s) for user request(s). For instance, the intent frame(s) may be suggested to elicit a request from a user. An intent frame is a natural language phrase (e.g., a sentence) that includes at least one carrier phrase and at least one slot. A slot in an intent frame is a placeholder that is identified as being replaceable by one or more words that identify an entity and/or an action to indicate an intent of the user. A carrier phrase in an intent frame includes one or more words that suggest a type of entity and/or action that is to be identified by the one or more words that may replace the corresponding slot. In accordance with these techniques, the intent frame(s) are suggested in response to determining that natural language functionality of a processing system is activated.