Event Causality Extraction (ECE) aims at extracting causal event pairs from texts. Despite ChatGPT’s recent success, fine-tuning small models remains the best approach for the ECE task. However, existing fine-tuning based ECE methods cannot ...

Identifying the causal relations between events is an important task in natural language processing (NLP). However, existing methods mainly leverage human empirical information about causality from limited labeled corpus or pseudo-data, which ...

• A novel cognitively-inspired method for the event causality identification task.
• Application of dual process theory in natural language processing.
• Parallel competition between the intuitive and the logical reasoning processes.

Label noises, categorized into closed-set noise and open-set noise, are prevalent in real-world scenarios and can seriously hinder the generalization ability of models. Identifying noise is challenging because noisy samples closely resemble true ...

Subevent relation identification (SRI) is a challenging natural language processing task of great value for knowledge acquisition and reasoning. Given an event pair, previous work mainly defines SRI as a classification task and usually relies on ...

Recently, ChatGPT, a representative large language model (LLM), has gained considerable attention. Due to their powerful emergent abilities, recent LLMs are considered as a possible alternative to structured knowledge bases like knowledge graphs (KGs). ...

In China, high-speed trains have become a major means of transportation for the masses. When the passengers wearing pacemakers travel on high-speed trains, electromagnetic environment in the carriage where the GSM-R voice and data antennae are located ...

A multifunctional frequency-selective rasorber (MFSR) with passband stealth performance by using PIN diodes is investigated, which is made up of two reconfigurable components (a lossy layer and transmissive polarization converter surface (lossless layer))...

This article presents an ultrathin chiral metasurface which can exhibit multiband asymmetric absorption as well as symmetric transmission in a specific frequency band outside the absorption regions. Unlike most electromagnetic metasurface absorbers, the ...

Antenna systems with more complicated geometries have been created as a result of evolving technology and rising performance standards in the industry. The geometric complexity of modern antennas makes it difficult for circuit theory tools or parametric ...

Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and generalization by ...

Understanding temporal commonsense concepts, such as times of occurrence and durations, is crucial for event-centric language understanding. Reasoning about such temporal concepts in a complex context requires reasoning over both the stated context and ...

A novel design approach to wideband, triple-mode resonant microstrip patch antenna with enhanced backfire gain and low side-lobe level, is advanced. The antenna consists of a 2.0-wavelength sectorial magnetic dipole and an annular sector reflector which ...

In this paper, a novel switchable bandpass filter is proposed. By switching p-i-n diodes on/off, the proposed filter can be switched between the single-band bandpass filter and the dual-band bandpass filter. The filter is mainly composed of eight pairs of ...

This study introduces a novel phase compensation-based, asymmetric frequency selective surface (FSS). Aimed at enhancing angular stability, the phase compensation method utilizes the reflected phase gradient changes generated by two FSSs at large grazing ...

This paper presents a design of a wide-angle scanning planar array based on a reconfigurable antenna with four radiation patterns for 5G applications. The pattern-reconfigurable antennas (PRAs), capable of switching into four radiation patterns with the ...

The WiFi-5 band was the most popular WiFi band until the Federal Communications Commission (FCC) announced a new spectrum of 6 GHz WiFi (5.925–7.125 GHz) for unlicensed users. Our proposed work is about to cover both the 5 GHz and 6 GHz WiFi bands. These ...

A circular polarization (CP) antenna that can switch between right-handed circular polarization (RHCP) and left-handed circular polarization (LHCP) modes has been designed and introduced for 5G applications in the 3.5 GHz frequency band in this work. The ...

Modern communication demands a low-profile, versatile antenna. In this paper, a low-profile antenna of size 38×40×0.787 mm3 is proposed to reconfigure frequency and radiation pattern. The Rogers RT Duroid 5870 of dielectric constant 2.33 is used as a substrate. ...

In this paper, a wearable dual-band T-shaped antenna using a coplanar waveguide (CPW) fed operating at 2.4 GHz and 5.2 GHz bands is proposed for onbody wireless communications applications. Without the metamaterial-based electromagnetic bandgap (EBG) ...

Transformer-based pretrained language models have shown promising performances in various textual inference tasks. However, additional relational knowledge between the semantic units within the input text may also play a critical role ...

• Our approach effectively utilize sparse knowledge bases to enhance language models.