Facebook, Inc.

Google Inc.

Alexander Matthew Rush

Ruchi Sanghvi

Thomas Scott Whitnah

Ding Zhou

Jason Edward Weston

Sumit Chopra

Slav Petrov

In one embodiment, a sequence of input words is received. Each of the input words is encoded as an indicator vector, wherein a sequence of the indicator vectors captures features of the sequence of input words. The sequence of the indicator vectors is then mapped to a distribution of a contextual probability of a first output word in a sequence of output words. For each subsequent output word, the sequence of the indicator vectors is encoded with a context, wherein the context comprises a previously mapped contextual probability distribution of a fixed window of previous output words; and the encoded sequence of the indicator vectors and the context is mapped to the distribution of the contextual probability of the subsequent output word. Finally, a condensed summary is generated using a decoder by maximizing the contextual probability of each of the output words.

Abstractive sentence summarization

Applications in social networks support interaction between members through various types of channels such as notifications, newsfeed, and so forth. For each channel, applications are ranked based on their user affinity measures. User affinity is based on measuring positive and negative interactions by users as both senders and recipients of messages generated by applications. Metrics are computed for the different types of messages and interactions provided by applications. For each channel, an application receives user affinity score based on specific weighted combination of the metrics. Applications use channel resources to send messages to increase their user base. Given the large number of applications that are available, the extent to which applications are allowed to use channels is controlled, limiting their resource consumption. User affinity scores of applications calculated for a channel are used to decide the allocation of channel resources for an application.

Resource management of social network applications

A computer-implemented method can include receiving a speech input representing a question, converting the speech input to a string of characters, and obtaining tokens each representing a potential word. The method can include determining one or more part-of-speech (POS) tags for each token and determining sequences of the POS tags for the tokens, each sequence of the POS tags including one POS tag per token. The method can include determining one or more parses for each sequence of the POS tags for the tokens and determining a most-likely parse and its corresponding sequence of the POS tags for the tokens to obtain a selected parse and a selected sequence of the POS tags for the tokens. The method can also include determining a most-likely answer to the question using the selected parse and the selected sequence of the POS tags for the tokens and outputting the most-likely answer.

Techniques for discriminative dependency parsing

A dependency parsing method can include determining an index set of possible head-modifier dependencies for a sentence. The index set can include inner arcs and outer arcs, inners arcs representing possible dependency between words in the sentence separated by a distance less than or equal to a threshold and outer arcs representing possible dependency between words in the sentence separated by a distance greater than the threshold. The index set can be pruned to include: (i) each specific inner arc when a likelihood that the specific inner arc is appropriate is greater than a first threshold, and (ii) the outer arcs when a likelihood that there exists any possible outer arc that is appropriate is greater than the first threshold. The method can include further pruning the pruned index set based on a second parsing algorithm, and determining a most-likely parse for the sentence from the pruned index set.

Growing community of inventors

Sunnyvale, CA, United States of America

Alexander Matthew Rush