The reviewed record of science sign in
Pith

arxiv: 1810.08802 · v1 · pith:V62WCC36 · submitted 2018-10-20 · cs.CL · cs.LG· stat.ML

Hierarchical Text Generation using an Outline

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:V62WCC36record.jsonopen to challenge →

classification cs.CL cs.LGstat.ML
keywords textgenerationoutlinehumanlanguagebecomesevaluationfind
0
0 comments X
read the original abstract

Many challenges in natural language processing require generating text, including language translation, dialogue generation, and speech recognition. For all of these problems, text generation becomes more difficult as the text becomes longer. Current language models often struggle to keep track of coherence for long pieces of text. Here, we attempt to have the model construct and use an outline of the text it generates to keep it focused. We find that the usage of an outline improves perplexity. We do not find that using the outline improves human evaluation over a simpler baseline, revealing a discrepancy in perplexity and human perception. Similarly, hierarchical generation is not found to improve human evaluation scores.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.