Naver Corporation

Conduent Business Services, LLC

Joseph Rozen

Hady Elsahar

Frédéric Roulland

Matthias Galle

German Kruszewski

Julien Wuthrich

A method for a language model applies in-context learning to detect problematic text and reformulate the problematic text to correct problematic text by (a) receiving, in the language model, a user generated text example; (b) determining if the user generated text example is a problematic text having a determined classification; (c) reformulating the user generated text example if the text example is a problematic text having the determined classification; (d) outputting the user generated text example if the text example is determined to be not a problematic text having the determined classification; and (e) outputting the reformulated text example if the text example is determined to be a problematic text having the determined classification.

Method for applying in-context learning for self-healing of language models

There is disclosed a computer-implemented method for detecting machine-generated documents in a collection of documents including machine-generated and human-authored documents. The computer-implemented method includes computing a set of long-repeated substrings (such as super-maximal repeats) with respect to the collection of documents and using a subset of the long-repeated substrings to designate documents containing the subset of the repeated substrings as machine-generated. The documents designated as machine-generated serve as positive examples of machine-generated documents and a set of documents including at least one human-authored document serves as negative examples of machine-generated documents. A plurality of classifiers are trained with a dataset including both the positive and negative examples of machine-generated documents. Classified output of the classifiers is then used to detect an extent to which a given document of the dataset is machine-generated.

Computer-implemented method for distributional detection of machine-generated text

A computer-implemented system and method for identifying passenger trips on a transportation network are described. The method includes acquiring transaction data for a collection of passengers boarding at stops on a transportation network. The network includes a plurality of routes. Route sequences are identified, based on the transaction data, each route sequence including at least two trip segments by a passenger. Each pair of trip segments of an identified route sequence are spaced by a transfer. For each identified route sequence, using a trip planner, the route sequence is classified as a multi-segment trip that includes at least one transfer or a multi-trip journey. A route sequence which is classified as a multi-trip journey is partitioned into at least two trips, each trip being a multi-segment trip or a single-segment trip.

Growing community of inventors

Grenoble, France

Joseph Rozen