抄録
This article delves into the scoring function of the statistical paraphrase generation model. It presents an algorithm for exact computation and two applicative experiments. The first experiment analyses the behaviour of a statistical paraphrase generation decoder, and raises some issues with the ordering of n-best outputs. The second experiment shows that a major boost of performance can be obtained by embedding a true score computation inside a Monte-Carlo sampling based paraphrase generator.
本文言語 | English |
---|---|
ページ | 144-152 |
ページ数 | 9 |
出版ステータス | Published - 2010 |
イベント | 23rd International Conference on Computational Linguistics, Coling 2010 - Beijing, China 継続期間: 2010 8月 23 → 2010 8月 27 |
Conference
Conference | 23rd International Conference on Computational Linguistics, Coling 2010 |
---|---|
国/地域 | China |
City | Beijing |
Period | 10/8/23 → 10/8/27 |
ASJC Scopus subject areas
- 言語および言語学
- 計算理論と計算数学
- 言語学および言語