Massachusetts Institute of Technology

International Business Machines Corporation

Tommi S Jaakkola

Yang Zhang

Shiyu Chang

Mo Yu

Klavs F Jensen

Connor Wilson Coley

Regina Barzilay

Wengong Jin

To improve actual labels that are produced by a black box computer classifier system from inputs, identify, using an environment-aware predictor and an environment-agnostic predictor, a subset of the inputs. The subset of the inputs has a stable correlation with the actual labels across a plurality of environments. Identify the subset of the inputs as an explanatory rationale for the actual labels. Display the explanatory rationale with the actual labels to a consumer of the actual labels. Optionally, in response to the explanatory rationale failing a rubric established by the consumer, generate revised inputs by removing the explanatory rationale from the inputs; and produce revised labels by processing the revised inputs with the environment-agnostic predictor.

Game-theoretic invariant rationalization of machine-learning results

A method and system of determining an output label rationale are provided. A first generator receives a first class of data and selects one or more input features from the first class of data. A first predictor receives the one or more selected input features from the first generator and predicts a first output label. A second generator receives a second class of data and selects one or more input features from the second class of data. A second predictor receives the one or more selected input features from the second generator and predicts a second output label. A discriminator receives the first and second output labels and determines whether the selected one or more input features from the first class of data or the selected features of the one or more input features from the second class of data, more accurately represents the first output label.

Game-theoretic frameworks for deep neural network rationalization

A method and system of training a natural language processing network are provided. A corpus of data is received and one or more input features selected therefrom by a generator network. The one or more selected input features from the generator network are received by a first predictor network and used to predict a first output label. A complement of the selected input features from the generator network are received by a second predictor network and used to predict a second output label.

Introspective extraction and complement control

Techniques for predicting a chemical reaction that includes a set of input molecules. The techniques may include obtaining input molecule information identifying the set of input molecules and predicting at least one chemical reaction that include a transformation between the set of input molecules and a set of output molecules by modifying at least one reaction center of the set of input molecules. The predicting of the at least one chemical reaction may be performed at least in part by using the input molecule information and at least one statistical model relating properties of atoms outside a region of a molecule to reactivity of the molecule at the region to identify the at least one reaction center. The techniques further include outputting information indicating the set of output molecules.

Growing community of inventors

Burlington, MA, United States of America

Tommi S Jaakkola