arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.01724cs.CL
收藏

摘要的推理时间风格控制

Inference Time Style Control for Summarization

University of Michigan(密歇根大学)

Shuyang Cao, Lu Wang

摘要:

如何生成不同风格的摘要,而不需要目标风格的语料库,或训练单独的模型?我们提出了两种新的方法,可以在任何预训练的基于transformer的摘要模型上进行摘要解码。(1)解码器状态调整通过外部训练的风格评分器即时修改解码器最终状态,以针对目标风格迭代地细化输出。(2)词单元预测约束词的使用,在生成过程中施加强大的词汇控制。在简单控制的总结实验中,自动评估和人类判断都发现我们的模型在更简单的语言中产生输出,同时仍然提供信息。我们还生成具有各种意识形态倾向的新闻标题,人类可以以合理的概率区分这些标题。

英文摘要:

How to generate summaries of different styles without requiring corpora in the target styles, or training separate models? We present two novel methods that can be deployed during summary decoding on any pre-trained Transformer-based summarization model. (1) Decoder state adjustment instantly modifies decoder final states with externally trained style scorers, to iteratively refine the output against a target style. (2) Word unit prediction constrains the word usage to impose strong lexical control during generation. In experiments of summarizing with simplicity control, automatic evaluation and human judges both find our models producing outputs in simpler languages while still informative. We also generate news headlines with various ideological leanings, which can be distinguished by humans with a reasonable probability.

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。

↑