Abstract: Systems and methods for natural language processing are described. One or more embodiments of the disclosure provide an entity matching apparatus trained using machine learning techniques to determine whether a query name corresponds to a candidate name based on a similarity score. In some examples, the query name and the candidate name are encoded using a character encoder to produce a regularized input sequence and a regularized candidate sequence, respectively. The regularized input sequence and the regularized candidate sequence are formed from a regularized character set having fewer characters than a natural language character set.

Abstract: Systems, methods, and non-transitory computer-readable media can generate a natural language model that provides user-entity differential privacy. For example, in one or more embodiments, a system samples sensitive data points from a natural language dataset. Using the sampled sensitive data points, the system determines gradient values corresponding to the natural language model. Further, the system generates noise for the natural language model. The system generates parameters for the natural language model using the gradient values and the noise, facilitating simultaneous protection of the users and sensitive entities associated with the natural language dataset. In some implementations, the system generates the natural language model through an iterative process (e.g., by iteratively modifying the parameters).

Abstract: Certain embodiments involve using a machine-learning tool to generate metadata identifying segments and topics for text within a document. For instance, in some embodiments, a text processing system obtains input text and applies a segmentation-and-labeling model to the input text. The segmentation-and-labeling model is trained to generate a predicted segment for the input text using a segmentation network. The segmentation-and-labeling model is also trained to generate a topic for the predicted segment using a pooling network of the model to the predicted segment. The output of the model is usable for generating metadata identifying the predicted segment and the associated topic.

Abstract: The present disclosure describes systems and methods for information retrieval. Embodiments of the disclosure provide a retrieval network that leverages external knowledge to provide reformulated search query suggestions, enabling more efficient network searching and information retrieval. For example, a search query from a user (e.g., a query mention of a knowledge graph entity that is included in a search query from a user) may be added to a knowledge graph as a surrogate entity via entity linking. Embedding techniques are then invoked on the updated knowledge graph (e.g., the knowledge graph that includes additional edges between surrogate entities and other entities of the original knowledge graph), and entities neighboring the surrogate entity are retrieved based on the embedding (e.g., based on a computed distance between the surrogate entity and candidate entities in the embedding space). Search results can then be ranked and displayed based on relevance to the neighboring entity.

Abstract: Systems and methods for natural language processing are described. Embodiments of the present disclosure identify a task set including a plurality of pseudo tasks, wherein each of the plurality of pseudo tasks includes a support set corresponding to a first natural language processing (NLP) task and a query set corresponding to a second NLP task; update a machine learning model in an inner loop based on the support set; update the machine learning model in an outer loop based on the query set; and perform the second NLP task using the machine learning model.

Abstract: The present disclosure provides a memory-based neural network for question answering. Embodiments of the disclosure identify meta-evidence nodes in an embedding space, where the meta-evidence nodes represent salient features of a training set. Each element of the training set may include a questions appended to a ground truth answer. The training set may also include questions with wrong answers that are indicated as such. In some examples, a neural Turing machine (NTM) reads a dataset and summarizes the dataset into a few meta-evidence nodes. A subsequent question may be appended to multiple candidate answers to form an input phrase, which may also be embedded in the embedding space. Then, corresponding weights may be identified for each of the meta-evidence nodes. The embedded input phrase and the weighted meta-evidence nodes may be used to identify the most appropriate answer.

Abstract: Embodiments of the disclosure provide a machine learning model for generating a predicted executable command for an image. The learning model includes an interface configured to obtain an utterance indicating a request associated with the image, an utterance sub-model, a visual sub-model, an attention network, and a selection gate. The machine learning model generates a segment of the predicted executable command from weighted probabilities of each candidate token in a predetermined vocabulary determined based on the visual features, the concept features, current command features, and the utterance features extracted from the utterance or the image.

Abstract: Systems and methods for key-phrase extraction are described. The systems and methods include receiving a transcript including a text paragraph and generating key-phrase data for the text paragraph using a key-phrase extraction network. The key-phrase extraction network is trained to identify domain-relevant key-phrase data based on domain data obtained using a domain discriminator network. The systems and methods further include generating meta-data for the transcript based on the key-phrase data.

Abstract: Techniques for training a language model for code switching content are disclosed. Such techniques include, in some embodiments, generating a dataset, which includes identifying one or more portions within textual content in a first language, the identified one or more portions each including one or more of offensive content or non-offensive content; translating the identified one or more salient portions to a second language; and reintegrating the translated one or more portions into the textual content to generate code-switched textual content. In some cases, the textual content in the first language includes offensive content and non-offensive content, the identified one or more portions include the offensive content, and the translated one or more portions include a translated version of the offensive content. In some embodiments, the code-switched textual content is at least part of a synthetic dataset usable to train a language model, such as a multilingual classification model.

Abstract: Techniques for training for and performing abstractive text summarization are disclosed. Such techniques include, in some embodiments, obtaining textual content, and generating a reconstruction of the textual content using a trained language model, the reconstructed textual content comprising an abstractive summary of the textual content generated based on relative importance parameters associated with respective portions of the textual content.

Abstract: Systems and methods for natural language processing are described. Embodiments of the present disclosure receive an input phrase including an aspect term; generate a complement phrase based on the input phrase using a language generator model, wherein the complement phrase includes different words than the input phrase; combine a representation of the input phrase and a representation of the complement phrase to obtain an augmented representation of the input phrase; and generate sentiment information corresponding to the aspect term based on the augmented representation.

Abstract: Techniques and systems are provided for predicting answers in response to one or more input queries. For instance, text from a corpus of text can be processed by a reader to generate one or multiple question and answer spaces. A question and answer space can include answerable questions and the answers associated with the questions (referred to as “question and answer pairs”). A query defining a question can be received (e.g., from a user input device) and processed by a retriever portion of the system. The retriever portion of the system can retrieve an answer to the question from the one or more pre-constructed question and answer spaces, and/or can determine an answer by comparing one or more answers retrieved from the one or more pre-constructed question and answer spaces to an answer generated by a retriever-reader system.

Abstract: Embodiments of the present invention provide systems, methods, and non-transitory computer storage media for parsing a given input referring expression into a parse structure and generating a semantic computation graph to identify semantic relationships among and between objects. At a high level, when embodiments of the preset invention receive a referring expression, a parse tree is created and mapped into a hierarchical subject, predicate, object graph structure that labeled noun objects in the referring expression, the attributes of the labeled noun objects, and predicate relationships (e.g., verb actions or spatial propositions) between the labeled objects. Embodiments of the present invention then transform the subject, predicate, object graph structure into a semantic computation graph that may be recursively traversed and interpreted to determine how noun objects, their attributes and modifiers, and interrelationships are provided to downstream image editing, searching, or caption indexing tasks.

Abstract: This disclosure involves executing artificial intelligence models that infer image editing operations from natural language requests spoken by a user. Further, this disclosure performs the inferred image editing operations using inferred parameters for the image editing operations. Systems and methods may be provided that infer one or more image editing operations from a natural language request associated with a source image, locate areas of the source that are relevant to the one or more image editing operations to generate image masks, and performing the one or more image editing operations to generate a modified source image.

Abstract: Systems and methods for image captioning are described. One or more aspects of the systems and methods include generating a training caption for a training image using an image captioning network; encoding the training caption using a multi-modal encoder to obtain an encoded training caption; encoding the training image using the multi-modal encoder to obtain an encoded training image; computing a reward function based on the encoded training caption and the encoded training image; and updating parameters of the image captioning network based on the reward function.

Abstract: Systems and methods for item recommendation are described. One or more embodiments of the systems and methods include generating a hidden vector representation for each word of a source document; removing at least one word from the source document based on the hidden vector representation using a summarization network to obtain a summary document; filtering a plurality of candidate documents based on the source document to obtain a plurality of filtered candidate documents; comparing the summary document to each of the filtered candidate documents to obtain a ranking score for each of the filtered candidate documents; and identifying a relevant candidate document from the filtered candidate documents based on the ranking score.

Abstract: Techniques and systems are described for performing semantic text searches. A semantic text-searching solution uses a machine learning system (such as a deep learning system) to determine associations between the semantic meanings of words. These associations are not limited by the spelling, syntax, grammar, or even definition of words. Instead, the associations can be based on the context in which characters, words, and/or phrases are used in relation to one another. In response to detecting a request to locate text within an electronic document associated with a keyword, the semantic text-searching solution can return strings within the document that have matching and/or related semantic meanings or contexts, in addition to exact matches (e.g., string matches) within the document. The semantic text-searching solution can then output an indication of the matching strings.

Abstract: Systems and methods for natural language processing are described. One or more embodiments of the present disclosure generate a word representation vector for each word of a text comprising an event trigger word and an argument candidate word; generate a dependency tree based on the text and the word representation vector; determine that at least one word of the text is independent of a relationship between the event trigger word and the argument candidate word; remove the at least one word from the dependency tree based on the determination to obtain a pruned dependency tree; generate a modified representation vector for each word of the pruned dependency tree using a graph convolutional network (GCN); and identify the relationship between the event trigger word and the argument candidate word based on the modified representation vector for each word of the pruned dependency tree.

Abstract: The present disclosure relates to systems and methods for automatically processing images based on a user request. In some examples, a request is divided into a retouching command (e.g., a global edit) and an inpainting command (e.g., a local edit). A retouching mask and an inpainting mask are generated to indicate areas where the edits will be applied. A photo-request attention and a multi-modal modulation process are applied to features representing the image, and a modified image that incorporates the user's request is generated using the modified features.

Abstract: Embodiments of the present invention provide systems, methods, and non-transitory computer storage media for parsing a given input referring expression into a parse structure and generating a semantic computation graph to identify semantic relationships among and between objects. At a high level, when embodiments of the preset invention receive a referring expression, a parse tree is created and mapped into a hierarchical subject, predicate, object graph structure that labeled noun objects in the referring expression, the attributes of the labeled noun objects, and predicate relationships (e.g., verb actions or spatial propositions) between the labeled objects. Embodiments of the present invention then transform the subject, predicate, object graph structure into a semantic computation graph that may be recursively traversed and interpreted to determine how noun objects, their attributes and modifiers, and interrelationships are provided to downstream image editing, searching, or caption indexing tasks.