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 2006.03773cs.CLcs.LG
收藏

法律辩论的挑战和刺激

Challenges and Thrills of Legal Arguments

UC Santa Barbara(加州大学圣巴巴拉分校)

Anurag Pallaprolu, Radha Vaidya, Aditya Swaroop Attawar

摘要:

最先进的基于注意力的模型,主要集中在Transformer架构,解决了使用所谓的缩放点积注意力的序列到序列转换的问题。虽然这种技术对于估计令牌间注意力非常有效,但当我们处理类似对话的场景时,它并不能回答序列间注意力的问题。我们提出了一个扩展,HumBERT,试图使用本地训练的Transformers执行连续的上下文参数生成。

英文摘要:

State-of-the-art attention based models, mostly centered around the transformer architecture, solve the problem of sequence-to-sequence translation using the so-called scaled dot-product attention. While this technique is highly effective for estimating inter-token attention, it does not answer the question of inter-sequence attention when we deal with conversation-like scenarios. We propose an extension, HumBERT, that attempts to perform continuous contextual argument generation using locally trained transformers.

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。

↑