Predicting bankruptcy is crucial for managing financial risk in corporations. This study emphasizes incorporating the auditor’s opinion text into prediction models to improve their ability to assess financial health. These opinions provide essential ...

In traditional lexical chain extraction tasks, researchers typically focus on identifying simple lexical items based on surface grammatical relations, often overlooking compound words with underlying semantic frameworks. To address this limitation,...

Metaphor Components Identification (MCI) contributes to enhancing machine understanding of metaphors, thereby advancing downstream natural language processing tasks. However, the complexity, diversity, and dependency on context and background ...${\mathrm{}}^{\mathit{}}$

Quality Estimation (QE) for machine translation aims to evaluate translation quality without reference translations. The WMT 2022 competition introduced a novel QE task focused on predicting MQM labels, i.e. human annotations for the locations, ...

Automatic speech recognition (ASR) is a crucial technology in the field of artificial intelligence, widely applied in modern society. The deep learning-based ASR method offers a simpler training framework and higher recognition rates compared to ...

Curriculum Learning, as a deep learning training strategy, has proven its effectiveness across many Natural Language Processing (NLP) and Multi-modal tasks. However, traditional Curriculum Learning is often instance-level, which requires manually ...

Implicit Discourse Relation Recognition (IDRR) is a challenging but vital task in discourse analysis that focuses on identifying and classifying the relation between two arguments without explicit connectives. Previous research has focused on ...

The goal of KD is to transfer valuable knowledge from a strong teacher model to a weaker student model in order to bridge the performance gap. However, the conventional teacher-student paradigm of KD can not be applied to the teacher model and ...

Class-incremental learning (CIL) has been widely applied in the real world due to its flexibility and scalability. Recent advancements in CIL have achieved outstanding performance. However, deep neural networks, including CIL models, face ...

Scene Text Recognition (STR) in dynamic driving scenes is important for recognizing real-world kilometer marker to facilitate the scheduling and operation of industrial scenes. For example, the location information of the train affects the safe ...

Achieving a high-quality and fine-grained appearance representation is an important task in Multi-Object Tracking (MOT). Recent works learn responses of different locations or channels from the global feature map to enhance visible parts or weaken ...

Driving scenes are extremely diverse and complicated that it is impossible to collect all cases with human effort alone. While data augmentation is an effective technique to enrich the training data, existing methods for camera data in autonomous ...

Semi-supervised medical image segmentation utilizes a large number of unlabeled images in combination with a limited number of labeled images for model training and optimization, significantly reducing the reliance on large-scale labeled images. ...

CAT technology, utilizing translation memory and quality control tools, boosts translation efficiency and consistency. Yet, it faces challenges with cultural nuances, context, and creativity, requiring human intervention. This study explores leveraging ...

In computational pathology, researchers often face challenges due to the scarcity of labeled pathology datasets. Data augmentation emerges as a crucial technique to mitigate this limitation. In this study, we introduce an efficient data ...

Neural combinatorial optimization (NCO) is a promising learning-based approach to solving complex combinatorial optimization problems such as the traveling salesman problem (TSP), the vehicle routing problem (VRP), and the orienteering problem (OP). ...

Data augmentation plays a crucial role in addressing the challenge of limited expert-annotated datasets in deep learning applications for retinal Optical Coherence Tomography (OCT) scans. This work exhaustively investigates the impact of various ...

Photosensitivity is a neurophysiological condition in which the brain produces epileptic discharges, known as Photoparoxysmal Responses, as a reaction to light flashes which may lead to seizures. The standardized diagnosis procedure consists of ...

Recommendation systems that use auxiliary information such as product names and categories have been proposed to address the cold-start problem. However, these methods do not perform well when we only have insufficient warm-start training data. On the ...

Sequential recommendation aims to provide users with personalized suggestions based on their historical interactions. When training sequential models, padding is a widely adopted technique for two main reasons: 1) The vast majority of models can only ...