Abstract: A system for reinforcement learning based controlled natural language generation is disclosed. The system includes a token generator subsystem to generate an initial output phrase including a sequence of output tokens. The system includes trained models associated with corresponding predefined tasks. Each trained model includes an attention layer to compute attention-based weights for each output token. The trained models include a scoring layer to generate a phrase sequence level score for the output phrase. The trained models include a reward generation layer to generate dense rewards for each output token based on the attention-based weights and the phrase sequence level score. The trained models include a feedback score generation layer to generate a feedback score based on the dense rewards and reward weights assigned to the dense rewards of the corresponding trained models. The feedback score generation layer provides the feedback score iteratively to the token generator subsystem.

Abstract: A system for classification of a customer query is disclosed. The system includes a customer interaction subsystem to receive the customer query from a customer, and a tokenizer subsystem to split the customer query into tokens. The system also includes a multitask profiler subsystem including a mapping module to map the tokens with pre-trained embedding data to assign mathematical codes to the tokens, an attention module to apply attention models hierarchically on a contextual embedding layer to obtain contextual mathematical codes corresponding to the tokens based on the mathematical codes, a classification module to classify the multiple tokens into profiles based on the contextual mathematical codes, and a profile generator to generate a human readable profile and a machine-readable profile based on the profiles. The machine-readable profile and the human readable profile includes at least one of a customer profile, a product profile, an issue profile or a combination thereof.

Abstract: Embodiments are provided for reducing unwanted messages or spam within a real-time social networking service. According to certain aspects, a synchronous analysis module may operate in coordination with an asynchronous analysis module. Each of the synchronous analysis module and the asynchronous analysis module analyzes an incoming message from a user account to determine whether the incoming message has characteristics of spam, whereby the synchronous analysis is at a lower latency than the asynchronous analysis. The asynchronous analysis is afforded the ability to identify certain spam characteristics that the synchronous analysis may identify during its lower latency analysis.

Abstract: A system for reinforcement learning based controlled natural language generation is disclosed. The system includes a token generator subsystem to generate an initial output phrase including a sequence of output tokens. The system includes trained models associated with corresponding predefined tasks. Each trained model includes an attention layer to compute attention-based weights for each output token. The trained models include a scoring layer to generate a phrase sequence level score for the output phrase. The trained models include a reward generation layer to generate dense rewards for each output token based on the attention-based weights and the phrase sequence level score. The trained models include a feedback score generation layer to generate a feedback score based on the dense rewards and reward weights assigned to the dense rewards of the corresponding trained models. The feedback score generation layer provides the feedback score iteratively to the token generator subsystem.

Abstract: A system for summarization of customer interaction is disclosed. The system includes a customer interaction subsystem to receive an input corpus. The system includes a token scorer including an issue prediction module to receive multiple tokens by splitting the input corpus. The issue prediction module includes the attention module to apply attention models hierarchically on the multiple tokens to obtain a machine-readable issue profile. The issue prediction module computes an issue prediction probability for each token based on the issue machine profile. The system includes a phrase extractor subsystem to extract phrases from the input corpus based on a set of predefined sentencing rules. The system includes a phrase selector subsystem to map each phrase with the corresponding issue prediction probability.

Abstract: A system for classification of a customer query is disclosed. The system includes a customer interaction subsystem to receive the customer query from a customer, and a tokenizer subsystem to split the customer query into tokens. The system also includes a multitask profiler subsystem including a mapping module to map the tokens with pre-trained embedding data to assign mathematical codes to the tokens, an attention module to apply attention models hierarchically on a contextual embedding layer to obtain contextual mathematical codes corresponding to the tokens based on the mathematical codes, a classification module to classify the multiple tokens into profiles based on the contextual mathematical codes, and a profile generator to generate a human readable profile and a machine-readable profile based on the profiles. The machine-readable profile and the human readable profile includes at least one of a customer profile, a product profile, an issue profile or a combination thereof.

Abstract: A system to generate digital responses to the customer query is disclosed. The system includes a customer interaction subsystem to receive one or more customer queries from a customer. The system also includes a multitask profiler subsystem operatively coupled to the customer interaction subsystem. The multitask profiler subsystem generates at least three human readable profiles and at least three machine-readable profiles based on the one or more customer queries. The system further includes a profile mapping subsystem operatively coupled to the multitask profiler subsystem. The profile mapping subsystem stores relation of each of the at least three machine readable profiles with each other.

Abstract: A system to generate digital responses to the customer query is disclosed. The system includes a customer interaction subsystem to receive one or more customer queries from a customer. The system also includes a multitask profiler subsystem operatively coupled to the customer interaction subsystem. The multitask profiler subsystem generates at least three human readable profiles and at least three machine-readable profiles based on the one or more customer queries. The system further includes a profile mapping subsystem operatively coupled to the multitask profiler subsystem. The profile mapping subsystem stores relation of each of the at least three machine readable profiles with each other.

Abstract: Embodiments are provided for reducing unwanted messages or spam within a real-time social networking service. According to certain aspects, a synchronous analysis module may operate in coordination with an asynchronous analysis module. Each of the synchronous analysis module and the asynchronous analysis module analyzes an incoming message from a user account to determine whether the incoming message has characteristics of spam, whereby the synchronous analysis is at a lower latency than the asynchronous analysis. The asynchronous analysis is afforded the ability to identify certain spam characteristics that the synchronous analysis may identify during its lower latency analysis.

Abstract: Embodiments are provided for reducing unwanted messages or spam within a real-time social networking service. According to certain aspects, a synchronous analysis module may operate in coordination with an asynchronous analysis module. Each of the synchronous analysis module and the asynchronous analysis module analyzes an incoming message from a user account to determine whether the incoming message has characteristics of spam, whereby the synchronous analysis is at a lower latency than the asynchronous analysis. The asynchronous analysis is afforded the ability to identify certain spam characteristics that the synchronous analysis may identify during its lower latency analysis.

Abstract: Embodiments are provided for reducing unwanted messages or spam within a real-time social networking service. According to certain aspects, a synchronous analysis module may operate in coordination with an asynchronous analysis module. Each of the synchronous analysis module and the asynchronous analysis module analyzes an incoming message from a user account to determine whether the incoming message has characteristics of spam, whereby the synchronous analysis is at a lower latency than the asynchronous analysis. The asynchronous analysis is afforded the ability to identify certain spam characteristics that the synchronous analysis may identify during its lower latency analysis.

Abstract: Embodiments are provided for reducing unwanted messages or spam within a real-time social networking service. According to certain aspects, a synchronous analysis module may operate in coordination with an asynchronous analysis module. Each of the synchronous analysis module and the asynchronous analysis module analyzes an incoming message from a user account to determine whether the incoming message has characteristics of spam, whereby the synchronous analysis is at a lower latency than the asynchronous analysis. The asynchronous analysis is afforded the ability to identify certain spam characteristics that the synchronous analysis may identify during its lower latency analysis.

Abstract: Embodiments are provided for reducing unwanted messages or spam within a real-time social networking service. According to certain aspects, a synchronous analysis module may operate in coordination with an asynchronous analysis module. Each of the synchronous analysis module and the asynchronous analysis module analyzes an incoming message from a user account to determine whether the incoming message has characteristics of spam, whereby the synchronous analysis is at a lower latency than the asynchronous analysis. The asynchronous analysis is afforded the ability to identify certain spam characteristics that the synchronous analysis may identify during its lower latency analysis.