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 2312.03367cs.CL
收藏

Lazy-k:用于受约束 Token 分类的解码方法

Lazy-k: Decoding for Constrained Token Classification

Shift Technology(Shift科技公司);L3i(L3i实验室)

Arthur Hemmer, Mickaël Coustaty, Nicola Bartolo, Jérôme Brachat, Jean-Marc Ogier

AI总结:

本文研究信息抽取中 token 分类的结构化预测问题,评估多种受约束解码方法并提出 Lazy-k,以在解码时间与准确率之间灵活权衡,显著提升概率模型、尤其是小模型的性能。

摘要:

我们探索了在结构化预测中改进概率模型的可能性。具体而言,我们在面向信息抽取的 token 分类任务背景下,将这些模型与受约束解码方法相结合。这些解码方法在最大化总概率的同时,搜索满足约束的标签分配。为此,我们评估了若干现有方法,并提出了一种名为 Lazy-k 的新型解码方法。研究结果表明,受约束解码方法能够显著提升模型性能,尤其是在使用较小模型时。Lazy-k 方法允许在解码时间与准确率之间实现更灵活的权衡。使用 Lazy-k 解码的代码可在以下地址获取:https://github.com/ArthurDevNL/lazyk。

英文摘要:

We explore the possibility of improving probabilistic models in structured prediction. Specifically, we combine the models with constrained decoding approaches in the context of token classification for information extraction. The decoding methods search for constraint-satisfying label-assignments while maximizing the total probability. To do this, we evaluate several existing approaches, as well as propose a novel decoding method called Lazy-$k$. Our findings demonstrate that constrained decoding approaches can significantly improve the models' performances, especially when using smaller models. The Lazy-$k$ approach allows for more flexibility between decoding time and accuracy. The code for using Lazy-$k$ decoding can be found here: https://github.com/ArthurDevNL/lazyk.

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。

↑