Techniques and Models for Multilingual Text Rewriting

A computer-implemented method for providing multilingual text rewriting according to a machine learning model, the method comprising:

• obtaining an input text sequence based on a set of text exemplars in a source language;
• generating, by a corruption module, a corrupted version of the input text sequence;
• receiving, by an encoder neural network of an encoder module, the corrupted version of the input text sequence;
• generating, by the encoder module, a set of encoded representations of the corrupted version of the input text sequence;
• extracting, by a style extractor module, a set of style vector representations associated with the input text sequence;
• receiving, by a decoder neural network of a decoder module, the set of encoded representations of the corrupted version of the input text sequence and the set of style vector representations, in which each style vector representation of the set is added element-wise to one of the set of encoded representations of the corrupted version of the input text sequence;
• outputting, by the decoder module, a set of rewritten texts in a plurality of languages different from the source language;
• and
• storing the rewritten text in selected ones of the plurality of languages according to a change in a least a sentiment or a formality of the input text sequence;
• wherein a set of model weights is shared by the encoder module and the style extractor module, and a unique token is appended to the input text sequence for style extraction instead of mean-pooling all of the style vector representations in the set.

A system comprising:

• a memory configured to store a set of text exemplars in a source language;
• and
• one or more processors operatively coupled to the memory, the one or more processors configured to:
• generate a corrupted version of an input text sequence based on the set of text exemplars in the source language;
• generate a set of encoded representations of a corrupted version of the input text sequence;
• extract a set of style vector representations associated with the input text sequence;
• generate a set of rewritten texts in a plurality of languages different from the source language based on the set of encoded representations and the set of style vector representations;
• and
• store, in the memory, the set of rewritten texts in selected ones of the plurality of languages based on one or more changes associated with the input text sequence.

A system comprising:

• a memory configured to store a set of text exemplars in a source language;
• an encoder configured to receive a corrupted version of an input text sequence based on the set of text exemplars in the source language and generate a set of encoded representations of the corrupted version of the input text sequence;
• and
• a decoder operably coupled to the encoder, the decoder configured to:
• receive the set of encoded representations of the corrupted version of the input text sequence and a set of style vector representations associated with the input text sequence, after each style vector representation is added element-wise to a respective encoded representation of the set of encoded representations, and
• output a set of rewritten texts in a plurality of languages different from the source language based on the set of encoded representations and the set of style vector representations,
• wherein the system is configured to provide rewritten texts in selected ones of the plurality of languages based on one or more changes associated with the input text sequence.