Правдоподобие
Related Papers
Embedding Open-domain Common-sense Knowledge from Text
AbstractOur ability to understand language often relies on common-sense knowledge ― background information the speaker can assume is known by the reader. Similarly, our comprehension of the language used in …...
Compressive Summarization with Plausibility and Salience Modeling
AbstractCompressive summarization systems typically rely on a seed set of syntactic rules to determine under what circumstances deleting a span is permissible, then learn which compressions to actually apply by …...
Employing Argumentation Knowledge Graphs for Neural Argument Generation
AbstractGenerating high-quality arguments, while being challenging, may benefit a wide range of downstream applications, such as writing assistants and argument search engines. Motivated by the effectiveness of utilizing knowledge graphs …...
Evaluating Saliency Methods for Neural Language Models
AbstractSaliency methods are widely used to interpret neural network predictions, but different variants of saliency methods often disagree even on the interpretations of the same prediction made by the same …...