The Curious Case of Degeneration: Difference between revisions
(Created page with "== Presented by == Donya Hamzeian == Introduction == Text generation is the act of automatically generating natural language texts like summarization, neural machine transla...") |
|||
| Line 3: | Line 3: | ||
== Introduction == | == Introduction == | ||
Text generation is the act of automatically generating natural language texts like summarization, neural machine translation, fake news generation and etc. Degeneration happens when the output text is incoherent or produces repetitive results. For example in figure 1, the GPT2 model tries to generate the continuation text given the context. On the left side, the beam-search was used as the decoding strategy which has obviously stuck in a repetitive loop. On the right side, however, you can see how the pure sampling decoding strategy has generated incoherent results. | Text generation is the act of automatically generating natural language texts like summarization, neural machine translation, fake news generation and etc. Degeneration happens when the output text is incoherent or produces repetitive results. For example in figure 1, the GPT2 model tries to generate the continuation text given the context. On the left side, the beam-search was used as the decoding strategy which has obviously stuck in a repetitive loop. On the right side, however, you can see how the pure sampling decoding strategy has generated incoherent results. | ||
[[File: GPT2_example.png | center |800px]] | |||
The authors argue that decoding strategies that are based on maximization like beam search lead to degeneration even with powerful models like GPT-2. Even though there are some utility functions that encourage diversity, they are not enough and the text generated by maximization, beam-search, or top-k sampling is too probable which indicates the lack of diversity (variance) compared to human-generated texts | The authors argue that decoding strategies that are based on maximization like beam search lead to degeneration even with powerful models like GPT-2. Even though there are some utility functions that encourage diversity, they are not enough and the text generated by maximization, beam-search, or top-k sampling is too probable which indicates the lack of diversity (variance) compared to human-generated texts | ||
Some may raise this question that the problem with beam-search may be due to search error i.e. they are more probable phrases that beam search is unable to find, but the point is that natural language has lower per-token probability on average and people usually optimize against saying the obvious. | Some may raise this question that the problem with beam-search may be due to search error i.e. they are more probable phrases that beam search is unable to find, but the point is that natural language has lower per-token probability on average and people usually optimize against saying the obvious. | ||
==Language Model Decoding== | ==Language Model Decoding== | ||
Revision as of 17:22, 7 November 2020
Presented by
Donya Hamzeian
Introduction
Text generation is the act of automatically generating natural language texts like summarization, neural machine translation, fake news generation and etc. Degeneration happens when the output text is incoherent or produces repetitive results. For example in figure 1, the GPT2 model tries to generate the continuation text given the context. On the left side, the beam-search was used as the decoding strategy which has obviously stuck in a repetitive loop. On the right side, however, you can see how the pure sampling decoding strategy has generated incoherent results.
The authors argue that decoding strategies that are based on maximization like beam search lead to degeneration even with powerful models like GPT-2. Even though there are some utility functions that encourage diversity, they are not enough and the text generated by maximization, beam-search, or top-k sampling is too probable which indicates the lack of diversity (variance) compared to human-generated texts
Some may raise this question that the problem with beam-search may be due to search error i.e. they are more probable phrases that beam search is unable to find, but the point is that natural language has lower per-token probability on average and people usually optimize against saying the obvious.