Parallel cross-lingual summarization data is scarce, requiring models to better use the limited available cross-lingual resources. Existing methods to do so often adopt sequence-to-sequence networks with multi-task frameworks. Such approaches apply …
Like humans, document summarization models can interpret a document's contents in a number of ways. Unfortunately, the neural models of today are largely black boxes that provide little explanation of how or why they generated a summary in the way …
This study focuses on multi-passage Machine Reading Comprehension (MRC) task. Prior work has shown that retriever, reader pipeline model could improve overall performance. However, the pipeline model relies heavily on retriever component since …