ABSTRACT Aspect‐based Sentiment Analysis (ABSA) is a vital NLP task that identifies sentiment towards specific entities or aspect terms within a text. Recently, large language models (LLMs) have shown impressive capabilities in semantic comprehension and logical inference. However, LLM hallucinations pose challenges in accurately determining sentiment polarity for aspect terms, leading to performance issues. Moreover, current ABSA methods often fail to fully leverage the vast prior knowledge embedded within LLMs, resulting in suboptimal classification outcomes for specific aspects. Inspired by these challenges, we propose the BYD‐OBS‐ABSA framework—‘Beyond Simple Observations, Embracing Comprehensive Contextual Insights’ for ABSA tasks. This framework leverages unique in‐context constraints, backgrounds, and analogical reasoning to address LLM hallucinations and uses self‐adaptive bootstrap instructions optimization to enhance LLM predictions. BYD‐OBS‐ABSA integrates various in‐context augmentation strategies, including emotion‐oriented backgrounds, constraints, and analogical reasoning. BYD‐OBS‐ABSA further improves initial LLM instructions through adaptive iterative optimization using a random search bootstrap algorithm, maximizing the benefits of LLM prompting. Extensive zero/few‐shot experiments with GPT‐3.5‐turbo across six public datasets validate the effectiveness and robustness of our framework, even surpassing human judgment in certain scenarios.

Fake news detection (FND) is a critical task in natural language processing (NLP) focused on identifying and mitigating the spread of misinformation. Large language models (LLMs) have recently shown remarkable abilities in understanding semantics and performing logical inference. However, their tendency to generate hallucinations poses significant challenges in accurately detecting deceptive content, leading to suboptimal performance. In addition, existing FND methods often underutilize the extensive prior knowledge embedded within LLMs, resulting in less effective classification outcomes. To address these issues, we propose the CAPE–FND framework, context‐aware prompt engineering, designed for enhancing FND tasks. This framework employs unique veracity‐oriented context‐aware constraints, background information, and analogical reasoning to mitigate LLM hallucinations and utilizes self‐adaptive bootstrap prompting optimization to improve LLM predictions. It further refines initial LLM prompts through adaptive iterative optimization using a random search bootstrap algorithm, maximizing the efficacy of LLM prompting. Extensive zero‐shot and few‐shot experiments using GPT‐3.5‐turbo across multiple public datasets demonstrate the effectiveness and robustness of our CAPE–FND framework, even surpassing advanced GPT‐4.0 and human performance in certain scenarios. To support further LLM–based FND, we have made our approach’s code publicly available on GitHub (our CAPE–FND code: https://github.com/albert-jin/CAPE-FND [Accessed on 2024.09]).

Most existing methods for predicting drug-drug interactions (DDI) predominantly concentrate on capturing the explicit relationships among drugs, overlooking the valuable implicit correlations present between drug pairs (DPs), which leads to weak predictions. To address this issue, this paper introduces a hierarchical multi-relational graph representation learning (HMGRL) approach. Within the framework of HMGRL, we leverage a wealth of drug-related heterogeneous data sources to construct heterogeneous graphs, where nodes represent drugs and edges denote clear and various associations. The relational graph convolutional network (RGCN) is employed to capture diverse explicit relationships between drugs from these heterogeneous graphs. Additionally, a multi-view differentiable spectral clustering (MVDSC) module is developed to capture multiple valuable implicit correlations between DPs. Within the MVDSC, we utilize multiple DP features to construct graphs, where nodes represent DPs and edges denote different implicit correlations. Subsequently, multiple DP representations are generated through graph cutting, each emphasizing distinct implicit correlations. The graph-cutting strategy enables our HMGRL to identify strongly connected communities of graphs, thereby reducing the fusion of irrelevant features. By combining every representation view of a DP, we create high-level DP representations for predicting DDIs. Two genuine datasets spanning three distinct tasks are adopted to gauge the efficacy of our HMGRL. Experimental outcomes unequivocally indicate that HMGRL surpasses several leading-edge methods in performance.

Recently, rumor detection (fake news detection) has seen a surge in research interest, and fact verification (fake news checking) has simultaneously become a significant research aspect. Despite the inherent distinction between fact verification and rumor detection – the former being a three-category task and the latter a binary one – there has yet to be in-depth exploration into the synergies between these two tasks. Furthermore, given the severe scarcity and the time-consuming and costly construction nature of fact verification datasets, few-shot/zero-shot fact verification methods are particularly favored. To tackle these challenges, we conduct a series of studies around “How can rumor detection enhance few-shot fact verification, and to what extent?”. Specifically, we systematically investigate the knowledge transferability between the two tasks, proposing a framework, Det2Ver, that is applicable to both rumor detection and fact verification. Through the construction of adaptive prompt templates and prompt-tuned LLMs like T5, Det2Ver structural-level synchronizes the two tasks and utilizes the external knowledge from rumor detection to reinforce fact verification task. We demonstrate the significance and effectiveness of Det2Ver. Through the few-shot/zero-shot experiments on three widely-used datasets, compared to other LLMs prompt-tuning baselines, the Det2Ver for cross-task knowledge augmentation brings a significant improvement in macro-F1 for fact verification.

With the explosive increase in the Internet of Things (IoT) devices, there is a rising demand for seamless and intuitive interactions between users and smart devices. Existing solutions require either dedicated sensors with microcontroller and battery power or modification of the hardware. This article presents RF-Keypad to realize a battery-free and wireless touch input interaction solution via commercial off-the-shelf (COTS) radio frequency identification (RFID) devices. RF-Keypad can easily turn an ordinary rigid object into an interaction touch keypad by deploying a tag array on the surface of the object. RF-Keypad extracts the received signal strength (RSS) variation feature of the touch action and builds an RSS-based model to detect the touch events, which is robust to the tag position and orientation. To acquire better performance, best touch area that poses distinct RSS variation feature is studied and optimal placement of the tag array is also investigated to eliminate mutual coupling effect between adjacent tags. Two touch detection algorithms based on RSS variance (RV) and the variance of the RSS variance (VoRV) are proposed, respectively, where the RV-based algorithm suits the scenario of fixed antenna-tag distance and the VoRV-based algorithm is designed for the scenario of variable antenna-tag distance. We implement a prototype of RF-Keypad with commodity RFID devices. Extensive experiments show that RF-Keypad achieves a touch detection accuracy of higher than 96% under fixed antenna-tag scenario and higher than 91% under variable antenna-tag distance scenario. An intelligent door access application is developed to highlight the practicality and scalability of our solution.

In the era of sustainable smart agriculture, a vast amount of agricultural news text is posted online, accumulating significant agricultural knowledge. To efficiently access this knowledge, effective text classification techniques are urgently needed. Deep learning approaches, such as fine-tuning strategies on pre-trained language models (PLMs), have shown remarkable performance gains. Nonetheless, these methods face several complex challenges, including limited agricultural training data, poor domain transferability (especially across languages), and complex and expensive deployment of large models. Inspired by the success of recent ChatGPT models (e.g., GPT-3.5, GPT-4), this work explores the potential of applying ChatGPT in the field of agricultural informatization. Various crucial factors, such as prompt construction, answer parsing, and different ChatGPT variants, are thoroughly investigated to maximize its capabilities. A preliminary comparative study is conducted, comparing ChatGPT with PLMs-based fine-tuning methods and PLMs-based prompt-tuning methods. Empirical results demonstrate that ChatGPT effectively addresses the mentioned research challenges and bottlenecks, making it an ideal solution for agricultural text classification. Moreover, ChatGPT achieves comparable performance to existing PLM-based fine-tuning methods, even without fine-tuning on agricultural data samples. We hope this preliminary study could inspire the emergence of a general-purpose AI paradigm for agricultural text processing.

Linguistic metonymy is a common type of figurative language in natural language processing (NLP), where a concept is represented by a closely associated word or phrase, for example “business executives suits”. As a result, metonymy resolution has become an important NLP task aimed at correctly identifying metonymic expressions within sentences. Previous approaches to this task have typically relied on pre-trained language models (PLMs) using a fine-tuning process. However, this can be time-consuming and resource-intensive, and may lead to a loss of factual prior knowledge. The emergence of a novel learning paradigm termed “prompt learning” or “prompt-tuning” has recently sparked widespread interest and captured considerable attention, as it has proven to yield remarkable results and surpass previous benchmarks. This approach uses a “pre-train→prompt→predict” paradigm and has been shown to better utilize the internal prior knowledge of a PLM, especially in situations with limited supervised resources. Inspired by this success, we investigated how prompt learning could improve metonymy resolution. We have developed a series of prompt learning approaches, called PromptMR, for metonymy resolution, and applied them to several widely-used metonymy resolution datasets. We also designed additional prompt-tuning augmentation strategies to further enhance the potential of prompt learning. Our experiments demonstrated that our method achieved state-of-the-art performance over multiple competitive baselines in both data-sufficient and data-scarce scenarios. The code implementations for PromptMR are accessible on GitHub via the URL: https://github.com/albert-jin/PromptTuning2MetonymyResolution.

Expression-level information extraction is a challenging task in natural language processing (NLP), which aims to retrieve crucial semantic information from linguistic documents. However, there is a lack of up-to-date data resources for accelerating expression-level information extraction, particularly in the Chinese financial high technology field. To address this gap, we introduce Fintech Key-Phrase: a human-annotated key-phrase dataset for the Chinese financial high technology domain. This dataset comprises over 12K paragraphs along with annotated domain-specific key-phrases. We extract the publicly released reports, Chinese management’s discussion and analysis (CMD&A), from the renowned Chinese research data services platform (CNRDS) and then filter the reports related to high technology. The high technology key-phrases are annotated following pre-defined philosophy guidelines to ensure annotation quality. In order to better understand the limitations and challenges in the purposed dataset, we conducted comprehensive noise evaluation experiments for the Fintech Key-Phrase, including annotation consistency assessment and absolute annotation quality evaluation. To demonstrate the usefulness of our released Fintech Key-Phrase in retrieving valuable information in the Chinese financial high technology field, we evaluate its significance using several superior information retrieval systems as representative baselines and report corresponding performance statistics. Additionally, we further applied ChatGPT to the text augmentation approach of the Fintech Key-Phrase dataset. Extensive comparative experiments demonstrate that the augmented Fintech Key-Phrase dataset significantly improved the coverage and accuracy of extracting key phrases in the finance and high-tech domains. We believe that this dataset can facilitate scientific research and exploration in the Chinese financial high technology field. We have made the Fintech Key-Phrase dataset and the experimental code of the adopted baselines accessible on Github: https://github.com/albert-jin/Fintech-Key-Phrase. To encourage newcomers to participate in the financial high-tech domain information retrieval research, we have developed a series of tools, including an open website 1 and corresponding real-time information retrieval APIs. 2

Due to the success of Bidirectional Encoder Representations from Transformers (BERT) in natural language process (NLP), the multi-head attention transformer has been more and more prevalent in computer-vision researches (CV). However, it still remains a challenge for researchers to put forward complex tasks such as vision detection and semantic segmentation. Although multiple Transformer-Based architectures like DETR and ViT-FRCNN have been proposed to complete object detection task, they inevitably decreases discrimination accuracy and brings down computational efficiency caused by the enormous learning parameters and heavy computational complexity incurred by the traditional self-attention operation. In order to alleviate these issues, we present a novel object detection architecture, named Convolutional vision Transformer-Based Attentive Single Shot MultiBox Detector (CvT-ASSD), that built on the top of Convolutional vision Transormer (CvT) with the efficient Attentive Single Shot MultiBox Detector (ASSD). We provide comprehensive empirical evidence showing that our model CvT-ASSD can leads to good system efficiency and performance while being pretrained on large-scale detection datasets such as PASCAL VOC and MS COCO. Code has been released on public github repository at https://github.com/albert-jin/CvT-ASSD.