arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.07649cs.CL
收藏

利用逆概率加权提高神经文本生成的多样性

Improving Diversity of Neural Text Generation via Inverse Probability Weighting

Central Conservatory of Music(中央音乐学院);Tsinghua University(清华大学)

Xinran Zhang, Maosong Sun, Jiafeng Liu, Xiaobing Li

摘要:

神经文本生成存在重复等文本退化问题。传统的随机抽样方法只关注截断分布中不可靠的“尾部”,而没有解决“头部”部分,我们发现这部分可能包含繁琐甚至重复的候选项,这些候选项有很高的概率导致重复循环。他们也没有考虑人类文本并不总是倾向于高概率词的问题。受此启发,在这项工作中,我们提出了一个启发式抽样方法。我们建议使用预测分布的四分位数范围来确定“头部”部分,然后用逆概率置换和重新缩放“头部”。这旨在降低具有较高概率的乏味且可能重复的候选项的概率,并增加具有较低概率的合理但更令人惊讶的候选项的概率。该算法提供了一个合理的排列的预测分布,提高了多样性,而不损害合理性的分布。我们使用预先训练好的语言模型来比较我们的算法和传统的方法。实验结果表明,该算法能有效地提高生成样本的多样性,同时达到与人类文本相似的效果。

英文摘要:

The neural text generation suffers from the text degeneration issue such as repetition. Traditional stochastic sampling methods only focus on truncating the unreliable "tail" of the distribution, and do not address the "head" part, which we show might contain tedious or even repetitive candidates with high probability that lead to repetition loops. They also do not consider the issue that human text does not always favor high-probability words. Inspired by these, in this work we propose a heuristic sampling method. We propose to use interquartile range of the predicted distribution to determine the "head" part, then permutate and rescale the "head" with inverse probability. This aims at decreasing the probability for the tedious and possibly repetitive candidates with higher probability, and increasing the probability for the rational but more surprising candidates with lower probability. The proposed algorithm provides a reasonable permutation on the predicted distribution which enhances diversity without compromising rationality of the distribution. We use pre-trained language model to compare our algorithm with traditional methods. Results show that our algorithm can effectively increase the diversity of generated samples while achieving close resemblance to human text.

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。

↑