No abstract

No abstract

No abstract

Relation extraction (RE) is an essential topic in natural language processing and has attracted extensive attention. Current RE approaches achieve fantastic results on common datasets, while they still struggle on practical applications. In this paper, we analyze the above performance gap, the underlying reason of which is that practical applications intrinsically have more hard cases. To make RE models more robust on such practical hard cases, we propose a case-oriented construction framework to build a Hard Case Relation Extraction Dataset (HacRED). The proposed HacRED consists of 65,225 relational facts annotated from 9,231 documents with sufficient and diverse hard cases. Notably, HacRED is one of the largest Chinese document-level RE datasets and achieves a high 96% F1 score on data quality. Furthermore, we apply the stateof-the-art RE models on this dataset and conduct a thorough evaluation. The results show that the performance of these models is far lower than humans, and RE applying on practical hard cases still requires further efforts. Ha-cRED is publicly available at https://github. com/qiaojiim/HacRED.

The Mo‐doped WSe2 nanolamellars have been successfully prepared via solid‐state thermal (750 °C) reaction between micro‐sized W, Mo with Se powders under inert atmosphere in a closed reactor and characterized by X‐ray diffractometer (XRD), scanning electron microscopy (SEM) and transmission electron microscopy (TEM). It was found that the morphologies of the as‐prepared products changed from microplates to nanolamellars to aggregations composed of nanoparticles with the doping of Mo powders. And the sizes of crystallites evidently reduced while the contents of dopant increased within a certain limit (1 wt.%–7 wt.%). The tribological properties of the as‐prepared products as additives in HVI750 base oil were investigated by UMT‐2 multispecimen tribotester. The friction coefficient of the base oil containing Mo‐doped WSe2 nanolamellars was lower and more stable than that of WSe2 nanolamellars. A combination of rolling friction, sliding friction, and stable tribofilm on the rubbing surface could further explain the good friction and wear properties of Mo‐WSe2 nanoparticles as additives than that of WSe2.