Diversity and Quality: Comparing Decoding Methods with PEGASUS for Text Summarization
No Thumbnail Available
Date
2021
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
none
This thesis offers three major contributions: (1) It considers a number of diverse decoding methods to address degenerate repetition in model output text and investigates what can be done to mitigate the loss in summary quality associated with the use of such methods. (2) It provides evidence that measure of textual lexical diversity (MTLD) is as viable tool as perplexity is for comparing text diversity in this context. (3) It presents a detailed analysis of the strengths and shortcomings of ROUGE, particularly in regard to abstractive summarization. To explore these issues the work analyzes the results of experiments run on the CNN/DailyMail dataset with the PEGASUS model.
This thesis offers three major contributions: (1) It considers a number of diverse decoding methods to address degenerate repetition in model output text and investigates what can be done to mitigate the loss in summary quality associated with the use of such methods. (2) It provides evidence that measure of textual lexical diversity (MTLD) is as viable tool as perplexity is for comparing text diversity in this context. (3) It presents a detailed analysis of the strengths and shortcomings of ROUGE, particularly in regard to abstractive summarization. To explore these issues the work analyzes the results of experiments run on the CNN/DailyMail dataset with the PEGASUS model.
Description
Keywords
none, summarization, diverse decoding, PEGASUS, ROUGE, lexical diversity