Systems and methods for providing explainability of natural language processing

A computer-implemented method, comprising:

• accessing, by a device operatively coupled to a processor, a plain text clinical sentence;
• generating, by the device and via execution of a first machine learning model, an assertion status classification label for a word of interest in the plain text clinical sentence;
• extracting, by the device and from a hidden attention layer of the first machine learning model, word-wise attention scores corresponding to the plain text clinical sentence;
• and
• rendering, by the device and on an electronic display, both the assertion status classification label and a graphical representation of the word-wise attention scores.

A computer program product for facilitating systems and methods for providing explainability of natural language processing, the computer program product comprising a non-transitory computer-readable memory having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

• access a plain text sentence;
• generate, via execution of a first machine learning model, an inferencing task result based on the plain text sentence;
• extract, from a hidden attention layer of the first machine learning model, word-wise attention scores corresponding to the plain text sentence;
• and
• render, on an electronic display, both the inferencing task result and a graphical representation of the word-wise attention scores.