Yahoo! Inc.

Meta Platforms, Inc.

Google Inc.

Facebook, Inc.

Otter.ai, Inc.

Facebook Technologies, LLC

Fuchun Peng

Benoit F Dumoulin

Kun Han

Yumao Lu

Nawaaz Ahmed

Francoise Beaufays

Emmanouil Koukoumidis

Marco J Zagha

Xin Li

Sam Song Liang

Yun Fu

Simon Lau

Wenhai Yang

Kaisuke Nakajima

Julius Cheng

Michael Robert Hanson

Zheng Zhou

Gelei Chen

Pedro Jose Moreno Mengibar

Brian Strope

Xiaohu Liu

Rajen Subba

Jinsong Yu

Kanury Kanishka Rao

Mohsen M Agsen

Jason Schissel

Bo Zeng

Xing Wei

Vivek Narayanan

Jiedan Zhu

Cheng Zhang

Diego Melendo Casado

Jakob Nicolaus Foerster

Hasim Sak

Trevor D Strohman

Fei Huang

Zhengping Zuo

Aleksey Sergeyevich Fadeev

Françoise Beaufays

Antoine Jean Bruguier

Anuj Kumar

Rosie Jones

Xin Lei

Howard Scott Roy

Ben M Shahshahani

Chetan Parag Gupta

Donald Metzler

Si Chen

Ke Li

Yinan Zhang

Zhe Liu

Shane Haladuick

George Harlow Mills

Nicholas Robin

Fei Sha

Jihang Li

Guowei Shieh

James Matthew Grichnik

Brian Patrick Strope

System and method for processing and presenting a conversation. For example, a system includes a sensor configured to capture an audio-form conversation, and a processor configured to automatically transform the audio-form conversation into a transformed conversation. The transformed conversation includes a synchronized text, and the synchronized text is synchronized with the audio-form conversation. Additionally, the system includes a presenter configured to present the transformed conversation including the synchronized text and the audio-form conversation.

Systems and methods for processing and presenting conversations

In one embodiment, a method includes accessing a decoded hypothesis corresponding to an utterance, computing a predicted probability of observing each token in the decoded hypothesis by having a local first machine-learning model process the decoded hypothesis, computing a confidence score for each token in the decoded hypothesis by having a second machine-learning model process the decoded hypothesis, where the confidence score indicates a degree of confidence for the token to be observed at its position, calculating a loss for the computed predicted probabilities of observing tokens in the decoded hypothesis based on the computed confidence scores, and updating parameters of the local first machine-learning model based on the calculated loss.

Private language model adaptation for speech recognition

In one embodiment, a method includes receiving a first user input from a first user, wherein the first user input comprises a partial request, presenting one or more suggested intent auto-completions corresponding to the partial request, receiving a selection by the first user of a first suggested intent auto-completion of the suggested intent auto-completions and a second user input, presenting one or more suggested slot auto-completions corresponding to one or more candidate slot-hypotheses corresponding to the second user input, respectively, wherein each of the candidate slot-hypotheses comprise a slot-suggestion, and wherein each suggested slot auto-completion comprises the second user input and the corresponding candidate slot-hypothesis, receiving a selection by the first user of a first suggested slot auto-completion of the suggested slot auto-completions, and presenting execution results of one or more tasks corresponding to the first suggested intent auto-completion and the first suggested slot auto-completion.

Contextual auto-completion for assistant systems

In one embodiment, a method includes, by a client system, receiving a user input from the first user of an online social network, where the user input is associated with a subject and an intent, determining whether one or more agents associated with the intent are able to resolve the user input, identifying, responsive to determining that the one or more agents are not able to resolve the user input, one or more entities related to the subject, where each identified entity is connected to the first user via the online social network, and presenting, at the client system, one or more recommendations to the first user corresponding to the one or more entities.

Suggestions for fallback social contacts for assistant systems

In one embodiment, a method includes, by one or more computing systems, receiving, from a client system via an assistant xbot, a first audio input from a user, parsing the first audio input to identify a request for a content digest from an online social network, retrieving a plurality of content objects from the online social network, each of the content objects being accessible by the user, generating a customized newsfeed summary based on a determined semantical meaning of each of the plurality of content objects, and sending, to the client system via the assistant xbot, instructions for presenting an audio clip to the user responsive to the request for the content digest, wherein the audio clip comprises the customized newsfeed summary.

Content suggestions for content digests for assistant systems

In one embodiment, a method includes receiving an indication of a trigger action by a first user at a client system, wherein the trigger action is associated with a priming content object, identifying related content objects associated with the priming content object, selecting recommended content objects based on the priming content object, the related content objects, and profile information of the first user, wherein each of the selected recommended content objects comprises entity information of entities associated with the priming content object, and presenting content suggestions at the client system, wherein each content suggestion comprises one of the selected recommended content objects.

Engaging users by personalized composing-content recommendation

The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating contextually relevant transcripts of voice recordings based on social networking data. For instance, the disclosed systems receive a voice recording from a user corresponding to a message thread including the user and one or more co-users. The disclosed systems analyze acoustic features of the voice recording to generate transcription-text probabilities. The disclosed systems generate term weights for terms corresponding to objects associated with the user within a social networking system by analyzing user social networking data. Using the contextually aware term weights, the disclosed systems adjust the transcription-text probabilities. Based on the adjusted transcription-text probabilities, the disclosed systems generate a transcript of the voice recording for display within the message thread.

Generating contextually relevant text transcripts of voice recordings within a message thread

A computing device receives a message including a request for a recommendation. A representation of a hypothetical ideal recommendation to provide in response to the message is determined based on the message content. Data regarding entities that are potential recommendations are retrieved from a data store, the data regarding each entity including a representation of the entity (e.g., a vector) derived from factual information about the entity and opinions of other users of the entity. Ranking scores are determined for at least a subset of the entities based on the difference between the entity representations and the representation of the hypothetical ideal recommendation. An entity to recommend is selected based on the ranking scores and a reply to the message is sent that identifies the selected entity.

Combining machine-learning and social data to generate personalized recommendations

In one embodiment, a method includes receiving a sharing request to share content generated during a current dialog session from a client system associated with a first user, identifying one or more content objects associated with the sharing request based on a natural-language understanding module, wherein the one or more content objects were previously generated during the current dialog session, determining one or more second users the sharing request is directed to based on a user profile associated with first user, and sending instructions for accessing one or more of the identified content objects to one or more client systems associated with the one or more second users.

Assisting users with efficient information sharing among social connections

In one embodiment, a method includes receiving, from a client system associated with a first user, a first audio input. The method includes generating multiple transcriptions corresponding to the first audio input based on multiple automatic speech recognition (ASR) engines. Each ASR engine is associated with a respective domain out of multiple domains. The method includes determining, for each transcription, a combination of one or more intents and one or more slots to be associated with the transcription. The method includes selecting, by a meta-speech engine, one or more combinations of intents and slots from the multiple combinations to be associated with the first user input. The method includes generating a response to the first audio input based on the selected combinations and sending, to the client system, instructions for presenting the response to the first audio input.

Speech recognition accuracy with natural-language understanding based meta-speech systems for assistant systems

In one embodiment, a method includes, by one or more computing systems, receiving a request from a user for a content digest from an online social network, retrieving one or more content objects associated with the online social network that are accessible by the user, determining a semantical-embedding for each retrieved content object based on a query model, determining one or more categories for each retrieved content object, generating a set of content suggestions for each retrieved content object based on the one or more categories associated with the content object and the semantical-embedding of the content object, ranking for each retrieved content object, the one or more content suggestions in the respective set based on a comparison of a semantical-embedding associated with each content suggestion to the semantical-embedding of the content object, and sending instructions for presenting the content digest to the user.

In one embodiment, a method includes, by one or more computing devices, receiving, from a client system associated with a first user of an online social network, an indication of a trigger action by the first user, wherein the trigger action is associated with a user activity, determining a first user context based on the trigger action, accessing one or more recommended content objects associated with the first user context, calculating a recommendation score for each recommended content object, generating one or more content suggestions comprising one of the one or more recommended content objects, respectively, each content suggestion corresponding to a recommended content object having a recommendation score above a threshold recommendation score, and sending, to the client system in response to the trigger action, instructions for presenting one or more of the content suggestions to the first user.

Recommending content with assistant systems

In one embodiment, a method includes receiving an indication of a trigger action by a first user, wherein the trigger action is associated with a priming content object, identifying one or more related content objects associated with the priming content object, generating a first feature vector representing the priming content object, the one or more related content objects, and profile information of the first user, accessing a plurality of second feature vectors representing a plurality of recommended content objects, respectively, selecting one or more of the recommended content objects based on comparisons between the first feature vector and the respective second feature vectors representing the recommended content objects, and sending, to a client system in response to the trigger action, instructions for presenting one or more content suggestions to the first user, wherein each content suggestion comprises one of the selected recommended content objects.

Growing community of inventors

Cupertino, CA, United States of America

Fuchun Peng