The traditional emotion–cause extraction task needs to give the exact emotion annotation contained in the document before extracting the cause. Different from this, the emotion–cause pair extraction (ECPE) task, which aims to extract emotion–cause pairs with causal relationships directly from the document, is a task proposed in the natural language processing field recently. At present, the task of ECPE is divided into two steps: emotion annotations and cause clause extraction, emotion–cause clause pair combining and filtering. In this article, we optimize these two steps. On the one hand, in the first step of ECPE, a mutual assistance single-task model proposed by us is used to replace the original multi-task model. On the other hand, the position information of the clause is added as an additional feature in the second step of ECPE. Furthermore, based on different levels of semantic features, we design three filtering models and explore their performance on ECPE tasks. The experimental results on the benchmark corpus show that our approach can make the ECPE task achieve better performance. Compared with the referenced method, F1-score is increased by 5.3%. Moreover, these optimization strategies improve the subtasks contained in ECPE to varying degrees.
Diabetic ulcer is the most common kind of chronic wound worldwide. Though great efforts have been devoted, diabetic ulcer still remains as a challenge that requires constant monitoring and management. In this work, a multifunctional zwitterionic hydrogel is developed to simultaneously detect two fluctuant wound parameters, pH and glucose level, to monitor the diabetic wound status. A pH indicator dye (phenol red) and two glucose sensing enzymes, glucose oxidase (GOx) and horseradish peroxidase (HRP), are encapsulated in the anti‐biofouling and biocompatible zwitterionic poly‐carboxybetaine (PCB) hydrogel matrix. The visible images are collected by a smartphone and transformed into RGB signals to quantify the wound parameters. Results show that the activity and stability of both two enzymes are improved within PCB hydrogel, and the Kcat/Km value of PCB‐HRP is ≈5.5 fold of free HRP in artificial wound exudate. This novel wound dressing can successfully monitor the pH range of 4–8 and glucose level of 0.1–10 × 10?3 m . Meanwhile, it also provides a moist healing environment that can promote diabetic wound healing. This multifunctional wound dressing may open vistas in chronic wound management and guide the diabetes treatment in clinical applications. 相似文献
Semiconductor lasers with monolithically integrated ring cavities exceeding 1 cm in perimeter were fabricated and characterized optically and electrically. Directional switching was observed, influenced by S-section seeding of unidirectional operation. The lasing threshold was identified by differential current-voltage measurements, which are also shown to be useful in monitoring directional switching. Mode beating was observed at three radio-frequency bands: 7.6, 15.2, and 22.9 GHz. 相似文献
Single‐walled carbon nanotubes (SWCNTs) are a class of 1D nanomaterials that exhibit extraordinary electrical and optical properties. However, many of their fundamental studies and practical applications are stymied by sample polydispersity. SWCNTs are synthesized in bulk with broad structural (chirality) and geometrical (length and diameter) distributions; problematically, all known post‐synthetic sorting methods rely on ultrasonication, which cuts SWCNTs into short segments (typically <1 µm). It is demonstrated that ultralong (>10 µm) SWCNTs can be efficiently separated from shorter ones through a solution‐phase “self‐sorting”. It is shown that thin‐film transistors fabricated from long semiconducting SWCNTs exhibit a carrier mobility as high as ≈90 cm2 V?1 s?1, which is ≈10 times higher than those which use shorter counterparts and well exceeds other known materials such as organic semiconducting polymers (<1 cm2 V?1 s?1), amorphous silicon (≈1 cm2 V?1 s?1), and nanocrystalline silicon (≈50 cm2 V?1 s?1). Mechanistic studies suggest that this self‐sorting is driven by the length‐dependent solution phase behavior of rigid rods. This length sorting technique shows a path to attain long‐sought ultralong, electronically pure carbon nanotube materials through scalable solution processing. 相似文献