arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1908.04319cs.LGcs.CLstat.ML
收藏

基于非似然训练的神经文本生成

Neural Text Generation with Unlikelihood Training

New York University(纽约大学);Facebook AI Research(脸书人工智能研究院);CIFAR Azrieli Global Scholar(加拿大高级研究所阿兹列利全球学者项目)

Sean Welleck, Ilia Kulikov, Stephen Roller, Emily Dinan, Kyunghyun Cho, Jason Weston

摘要:

神经文本生成是自然语言应用中的关键工具,但众所周知,其核心存在重大问题。特别是,标准的似然训练和解码会导致枯燥和重复的输出。虽然已经提出了一些事后修复,特别是顶部- $k$和核采样,但它们没有解决模型预测的令牌级概率很差的事实。在本文中,我们表明,似然目标本身是错误的,导致在一个模型中,分配太多的概率包含重复和频繁的单词序列,不像那些从人类训练分布。我们提出了一个新的目标,不似然训练,这迫使不太可能的世代被模型分配较低的概率。我们表明,令牌和序列级的不似然训练给出了较少的重复,不那么沉闷的文本,同时保持困惑,使用标准的贪婪或束搜索给出优越的一代。根据人类的评价,我们的方法与标准的束搜索也优于目前流行的解码方法的细胞核采样或束阻塞,从而提供了一个强大的替代现有的技术。

英文摘要:

Neural text generation is a key tool in natural language applications, but it is well known there are major problems at its core. In particular, standard likelihood training and decoding leads to dull and repetitive outputs. While some post-hoc fixes have been proposed, in particular top-$k$ and nucleus sampling, they do not address the fact that the token-level probabilities predicted by the model are poor. In this paper we show that the likelihood objective itself is at fault, resulting in a model that assigns too much probability to sequences containing repeats and frequent words, unlike those from the human training distribution. We propose a new objective, unlikelihood training, which forces unlikely generations to be assigned lower probability by the model. We show that both token and sequence level unlikelihood training give less repetitive, less dull text while maintaining perplexity, giving superior generations using standard greedy or beam search. According to human evaluations, our approach with standard beam search also outperforms the currently popular decoding methods of nucleus sampling or beam blocking, thus providing a strong alternative to existing techniques.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑