Current Location:home > Browse

1. chinaXiv:202010.00067 [pdf]


Bin Ji
Subjects: Computer Science >> Natural Language Understanding and Machine Translation

基于span的联合提取模型已显示出它们在实体识别和关系提取上的效率。 这些模型将文本span视为候选实体,并将span元组视为候选关系元组。 span语义表示在实体识别和关系提取中都是共享的,而现有模型无法很好地捕获这些候选实体和关系的语义。 为了解决这些问题,我们引入了基于span的联合提取框架和基于注意的语义表示。 特别地,注意力用于计算语义表示,包括span特定和上下文表示。 我们将进一步研究四种注意变量在生成上下文语义表示中的作用。 实验表明,我们的模型优于以前的系统,并在ACE2005,CoNLL2004和ADE上达到了最优的结果。

submitted time 2020-10-26 Hits4437Downloads567 Comment 0

2. chinaXiv:201609.00972 [pdf]

Study of tracking efficiency and its systematic uncertainty from $J/\psi \to p \overlinep \pi^+ \pi^-$ at BESIII

Wen-Long Yuan; Xiao-Cong Ai; Xiao-Bin Ji; Shen-Jian Chen; Yao Zhang; Ling-Hui Wu; Liang-Liang Wang; Ye Yuan
Subjects: Physics >> Nuclear Physics

Based on?J/ψ?events collected with the BESIII detector, with corresponding Monte Carlo samples, the tracking efficiency and its systematic uncertainty are studied using a control sample of?J/ψ→pp???π+π?. Validation methods and different factors influencing the tracking efficiency are presented in detail. The tracking efficiency and its systematic uncertainty for protons and pions with the transverse momentum and polar angle dependence are also discussed.

submitted time 2016-09-14 Hits715Downloads385 Comment 0

  [1 Pages/ 2 Totals]