Abstract: The present disclosure relates to techniques for identifying out-of-domain utterances.

Abstract: Techniques are disclosed for tuning hyperparameters of a model. Datasets are obtained for training the model and metrics are selected for evaluating performance of the model. Each metric is assigned a weight specifying an importance to the performance of the model. A function is created that measures performance based on the weighted metrics. Hyperparameters are tuned to optimize the model performance. Tuning the hyperparameters includes: (i) training the model that is configured based on a current values for the hyperparameters; (ii) evaluating a performance of the model using the function; (iii) determining whether the model is optimized for the metrics; (iv) in response to the model not being optimized, searching for a new values for the hyperparameters, reconfiguring the model with the new values, and repeating steps (i)-(iii) using the reconfigured model; and (v) in response to the model being optimized for the metrics, providing a trained model.

Abstract: The present disclosure relates to chatbot systems, and more particularly, to batching techniques for handling unbalanced training data when training a model such that bias is removed from the trained machine learning model when performing inference. In an embodiment, a plurality of raw utterances is obtained. A bias eliminating distribution is determined and a subset of the plurality of raw utterances is batched according to the bias-reducing distribution. The resulting unbiased training data may be input into a prediction model for training the prediction model. The trained prediction model may be obtained and utilized to predict unbiased results from new inputs received by the trained prediction model.

Abstract: Techniques for noise data augmentation for training chatbot systems in natural language processing. In one particular aspect, a method is provided that includes receiving a training set of utterances for training an intent classifier to identify one or more intents for one or more utterances; augmenting the training set of utterances with noise text to generate an augmented training set of utterances; and training the intent classifier using the augmented training set of utterances. The augmenting includes: obtaining the noise text from a list of words, a text corpus, a publication, a dictionary, or any combination thereof irrelevant of original text within the utterances of the training set of utterances, and incorporating the noise text within the utterances relative to the original text in the utterances of the training set of utterances at a predefined augmentation ratio to generate augmented utterances.

Abstract: Techniques for stop word data augmentation for training chatbot systems in natural language processing. In one particular aspect, a computer-implemented method includes receiving a training set of utterances for training an intent classifier to identify one or more intents for one or more utterances; augmenting the training set of utterances with stop words to generate an augmented training set of out-of-domain utterances for an unresolved intent category corresponding to an unresolved intent; and training the intent classifier using the training set of utterances and the augmented training set of out-of-domain utterances. The augmenting includes: selecting one or more utterances from the training set of utterances, and for each selected utterance, preserving existing stop words within the utterance and replacing at least one non-stop word within the utterance with a stop word or stop word phrase selected from a list of stop words to generate an out-of-domain utterance.

Abstract: Techniques are described to determine whether an input utterance is unrelated to a set of skill bots associated with a master bot. In some embodiments, a system described herein includes a training system and a master bot. The training system trains a classifier of the master bot. The training includes accessing training utterances associated with the skill bots and generating training feature vectors from the training utterances. The training further includes generating multiple set representations of the training feature vectors, where each set representation corresponds to a subset of the training feature vectors, and configuring the classifier with the set representations. The master bot accesses an input utterance and generates an input feature vector. The master bot uses the classifier to compare the input feature vector to the multiple set representations so as to determine whether the input feature falls outside and, thus, cannot be handled by the skill bots.

Abstract: Techniques disclosed herein relate to improving quality of classification models for differentiating different user intents by improving the quality of training samples used to train the classification models. Pairs of user intents that are difficult to differentiate by classification models trained using the given training samples are identified based upon distinguishability scores (e.g., F-scores). For each of the identified pairs of intents, pairs of training samples each including a training sample associated with a first intent and a training sample associated with a second intent in the pair of intents are ranked based upon a similarity score between the two training samples in each pair of training samples. The identified pairs of intents and the pairs of training samples having the highest similarity scores may be presented to users through a user interface, along with user-selectable options or suggestions for improving the training samples.

Abstract: Systems, devices, and methods of the present invention relate to text classification. A text classification system accesses an utterance of text. The utterance includes at least one word. The text classification system generates a parse tree for the utterance. The parse tree includes at least one terminal node with a word type. The terminal node represents a word of the utterance. The text classification system applies one or more rules to the text. The text classification system then classifies the utterance as a question or a request for an autonomous agent to perform an action.

Abstract: Techniques for improving quality of classification models for differentiating different user intents by improving the quality of training samples used to train the classification models are described. Pairs of user intents that are difficult to differentiate by classification models trained using the given training samples are identified based upon distinguishability scores (e.g., F-scores). For each of the identified pairs of intents, pairs of training samples each including a training sample associated with a first intent and a training sample associated with a second intent in the pair of intents are ranked based upon a similarity score between the two training samples in each pair of training samples. The identified pairs of intents and the pairs of training samples having the highest similarity scores may be presented to users through a user interface, along with user-selectable options or suggestions for improving the training samples.

Abstract: The present disclosure relates to chatbot systems, and more particularly, to techniques for identifying an explicit invocation of a chatbot and determining an input for the chatbot being invoked. In certain embodiments, explicit invocation analysis involves detecting an invocation name in an utterance. The invocation name is an identifier assigned to a particular chatbot. In response to detection of the invocation name, the utterance is refined for input to the particular chatbot by determining which parts of the utterance, if any, contain relevant information for the particular chatbot and generating a new utterance, using the relevant parts of the utterance, for processing by the particular chatbot. The refining can involve removal of a portion of the utterance associated with the invocation name.

Abstract: The present disclosure relates to chatbot systems, and more particularly, to techniques for detecting that there are multiple intents represented in an utterance and then matching each detected intent to an intent associated with a chatbot in a chatbot system. In certain embodiments, a chatbot system receives an utterance from a user. A language of the utterance is determined and a set of rules identified for the language of the utterance. The utterance is parsed to extract information relating to the sentence structure of the utterance. The set of one or more rules is used to (1) determine whether the utterance is formed of two or more parts that each correspond to a separate intent of a user, and (2) split the utterance into the two or more parts for separate processing including matching of each user intent to an intent configured for a chatbot.

Abstract: Techniques are described for invoking and switching between chatbots of a chatbot system. In some embodiments, the chatbot system is capable of routing an utterance received while a user is already interacting with a first chatbot in the chatbot system. For instance, the chatbot system may identify a second chatbot based on determining that (i) such an utterance is an invalid input to the first chatbot or (ii) that the first chatbot is attempting to route the utterance to a destination associated with the first chatbot. Identifying the second chatbot can involve computing, using a predictive model, separate confidence scores for the first chatbot and the second chatbot, and then determining that a confidence score for the second chatbot satisfies one or more confidence score thresholds. The utterance is then routed to the second chatbot based on the identifying of the second chatbot.

Abstract: Systems, devices, and methods of the present invention relate to text classification. A text classification system accesses an utterance of text. The utterance includes at least one word. The text classification system generates a parse tree for the utterance. The parse tree includes at least one terminal node with a word type. The terminal node represents a word of the utterance. The text classification system applies one or more rules to the text. The text classification system then classifies the utterance as a question or a request for an autonomous agent to perform an action.

Abstract: Techniques disclosed herein relate to improving quality of classification models for differentiating different user intents by improving the quality of training samples used to train the classification models. Pairs of user intents that are difficult to differentiate by classification models trained using the given training samples are identified based upon distinguishability scores (e.g., F-scores). For each of the identified pairs of intents, pairs of training samples each including a training sample associated with a first intent and a training sample associated with a second intent in the pair of intents are ranked based upon a similarity score between the two training samples in each pair of training samples. The identified pairs of intents and the pairs of training samples having the highest similarity scores may be presented to users through a user interface, along with user-selectable options or suggestions for improving the training samples.

Abstract: Systems, devices, and methods of the present invention relate to text classification. A text classification system accesses an utterance of text. The utterance includes at least one word. The text classification system generates a parse tree for the utterance. The parse tree includes at least one terminal node with a word type. The terminal node represents a word of the utterance. The text classification system applies one or more rules to the text. The text classification system then classifies the utterance as a question or a request for an autonomous agent to perform an action.

Abstract: A system and method for using an automated process to identify bugs in software code. The system can be used to assist with the development of large and complex software products. File-level and/or line-level code coverage information is used to automatically trace-test failures to development changes within the product source code over a specified period of time. Information as to the health of a software product and the test criteria it passes or fails is compared at a first time, when the product may have satisfied all test criteria, with the health of the product at a second time when the same criteria may be failing. This information can then be used to narrow down and/or identify specific product failures to a particular change or set of changes in the software code, before any manual analysis need be done.

Abstract: A system and method for using an automated process to identify bugs in software code. The system can be used to assist with the development of large and complex software products. File-level and/or line-level code coverage information is used to automatically trace-test failures to development changes within the product source code over a specified period of time. Information as to the health of a software product and the test criteria it passes or fails is compared at a first time, when the product may have satisfied all test criteria, with the health of the product at a second time when the same criteria may be failing. This information can then be used to narrow down and/or identify specific product failures to a particular change or set of changes in the software code, before any manual analysis need be done.