Abstract: Systems and methods for text simplification are described. Embodiments of the present disclosure identify a simplified text that includes original information from a complex text and additional information that is not in the complex text. Embodiments then compute an entailment score for each sentence of the simplified text using a neural network, wherein the entailment score indicates whether the sentence of the simplified text includes information from a sentence of the complex text corresponding to the sentence of the simplified text. Then, embodiments generate a modified text based on the entailment score, the simplified text, and the complex text, wherein the modified text includes the original information and excludes the additional information. Embodiments may then present the modified text to a user via a user interface.

Abstract: Embodiments are disclosed for generating an intelligent change summary are described. In some embodiments, a method of generating an intelligent change summary includes obtaining a representation of a plurality of versions of a document, determining a distance score based on a comparison of a first of version of the document and a second version of the document, the distance score representing a magnitude of changes made from the first version of the document to the second version of the document, and generating a change summary of the document based on the distance score.

Abstract: Embodiments provide systems, methods, and computer storage media for extracting semantic labels for field widgets of form fields in unfilled forms. In some embodiments, a processing device accesses a representation of a fillable widget of a form field of an unfilled form. The processing device generates an encoded input representing text and layout of a sequence of tokens in a neighborhood of the fillable widget. The processing device uses a machine learning model to extract a semantic label representing a field type of the fillable widget in view of the encoded input. The processing device causes execution of an action using the semantic label.

Abstract: Methods and systems are provided for facilitating generation of fillable document templates. In embodiments, a document having a plurality of tokens is obtained. Using a machine learned model, a token state is identified for each token of the plurality of tokens. Each token state indicates whether a corresponding token is a static token that is to be included in a fillable document template or a dynamic token that is to be excluded in the fillable document template. Thereafter, a fillable document template corresponding with the document is generated, wherein for each dynamic token of the document, the fillable document template includes a fillable field corresponding to the respective dynamic token.

Abstract: Methods and systems are provided for facilitating generation of fillable document templates. In embodiments, a document having a plurality of tokens is obtained. Using a machine learned model, a token state is identified for each token of the plurality of tokens. Each token state indicates whether a corresponding token is a static token that is to be included in a fillable document template or a dynamic token that is to be excluded in the fillable document template. Thereafter, a fillable document template corresponding with the document is generated, wherein for each dynamic token of the document, the fillable document template includes a fillable field corresponding to the respective dynamic token.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for pre-training entity extraction models to facilitate domain adaptation in resource-constrained domains. In an example embodiment, a first machine learning model is used to encode sentences of a source domain corpus and a target domain corpus into sentence embeddings. The sentence embeddings of the target domain corpus are combined into a target corpus embedding. Training sentences from the source domain corpus within a threshold of similarity to the target corpus embedding are selected. A second machine learning model is trained on the training sentences selected from the source domain corpus.

Abstract: Embodiments are disclosed for generating an intelligent change summary are described. In some embodiments, a method of generating an intelligent change summary includes obtaining a representation of a plurality of versions of a document, determining a distance score based on a comparison of a first of version of the document and a second version of the document, the distance score representing a magnitude of changes made from the first version of the document to the second version of the document, and generating a change summary of the document based on the distance score.

Abstract: A computer-implemented method for generating a question from an abstracted template is described. A non-limiting example of the computer-implemented method includes receiving, by a processor, a question. The method parses, by the processor, the question into a parse tree and abstracts, by the processor, an abstracted template from the parse tree. The method receives, by the processor, a domain schema and a domain knowledge base and generates, by the processor, a new question based on the abstracted template, the domain schema, and the domain knowledge base.

Abstract: A text summarization system auto-generates text summarization models using a combination of neural architecture search and knowledge distillation. Given an input dataset for generating/training a text summarization model, neural architecture search is used to sample a search space to select a network architecture for the text summarization model. Knowledge distillation includes fine-tuning a language model for a given text summarization task using the input dataset, and using the fine-tuned language model as a teacher model to inform the selection of the network architecture and the training of the text summarization model. Once a text summarization model has been generated, the text summarization model can be used to generate summaries for given text.

Abstract: A system for generating text using a trained language model comprises an encoder that includes a debiased language model that penalizes generated text based on an equalization loss that quantifies first and second probabilities of respective first and second tokens occurring at a first point in the generated text. The first and second tokens define respective first and second groups of people. The system further comprises a decoder configured to generate text using the debiased language model. The decoder is further configured to penalize the generated text based on a bias penalization loss that quantifies respective probabilities of the first and second tokens co-occurring with a generated word. The encoder and decoder are trained to produce the generated text using a task-specific training corpus.

Abstract: Certain embodiments involve using machine-learning tools that include Bidirectional Encoder Representations from Transformers (“BERT”) language models for predicting emotional responses to text by, for example, target readers having certain demographics. For instance, a machine-learning model includes, at least, a BERT encoder and a classification module that is trained to predict demographically specific emotional responses. The BERT encoder encodes the input text into an input text vector. The classification module generates, from the input text vector and an input demographics vector representing a demographic profile of the reader, an emotional response score.

Abstract: A computer-implemented method for generating a question from an abstracted template is described. A non-limiting example of the computer-implemented method includes receiving, by a processor, a question. The method parses, by the processor, the question into a parse tree and abstracts, by the processor, an abstracted template from the parse tree. The method receives, by the processor, a domain schema and a domain knowledge base and generates, by the processor, a new question based on the abstracted template, the domain schema, and the domain knowledge base.