標(biāo)題: Titlebook: Web and Big Data; 8th International Jo Wenjie Zhang,Anthony Tung,Hongjie Guo Conference proceedings 2024 The Editor(s) (if applicable) and [打印本頁] 作者: dejected 時間: 2025-3-21 17:58
書目名稱Web and Big Data影響因子(影響力)
書目名稱Web and Big Data影響因子(影響力)學(xué)科排名
書目名稱Web and Big Data網(wǎng)絡(luò)公開度
書目名稱Web and Big Data網(wǎng)絡(luò)公開度學(xué)科排名
書目名稱Web and Big Data被引頻次
書目名稱Web and Big Data被引頻次學(xué)科排名
書目名稱Web and Big Data年度引用
書目名稱Web and Big Data年度引用學(xué)科排名
書目名稱Web and Big Data讀者反饋
書目名稱Web and Big Data讀者反饋學(xué)科排名
作者: 護(hù)身符 時間: 2025-3-21 22:00 作者: 攤位 時間: 2025-3-22 04:20
CeER: A Nested Name Entity Recognition Model Incorporating Gaze Featuretask, human annotators still have strength in recognition of complex structures and professional fields. In this work, we propose a Cognition-enhancing Entity Recognition model (CeER), which introduces cognition-based data to improve the performance of nested name entity recognition. Specifically, w作者: Autobiography 時間: 2025-3-22 07:40
A Boundary Feature Enhanced Span-Based Nested Named Entity Recognition Methodes and show poor performance in recognizing Nested Named Entities (NNEs). Towards Nested Named Entity Recognition (NNER), span-based methods, as a mainstream, have been proposed recently. The effectiveness of identifying entity span, which can be regarded as sub-sequences of a sentence, directly aff作者: Implicit 時間: 2025-3-22 11:52 作者: DRILL 時間: 2025-3-22 13:28
Enhancing NER with?Sentence-Level Entity Detection as?an?Simple Auxiliary Taskver, NER models are traditionally reliant on extensive manual annotations, which is both laborious and costly. To address this challenge, we propose a simple yet effective multi-task learning framework that requires no additional labeling efforts. Our approach leverages the observation that nearly 3作者: Omniscient 時間: 2025-3-22 17:19 作者: Myocyte 時間: 2025-3-22 22:57
CeER: A Nested Name Entity Recognition Model Incorporating Gaze Featuretask, human annotators still have strength in recognition of complex structures and professional fields. In this work, we propose a Cognition-enhancing Entity Recognition model (CeER), which introduces cognition-based data to improve the performance of nested name entity recognition. Specifically, w作者: 牌帶來 時間: 2025-3-23 04:56
External Knowledge Enhancing Meta-learning Framework for?Few-Shot Text Classification via?Contrastivrototypical networks and so on. The primary mission of few-shot text classification is to learn a high-quality embedding representation for each class. However, due to the randomness in sample sampling, the representations of class prototypes often tend to be unstable. This paper proposes the SCLAWM作者: insipid 時間: 2025-3-23 08:04 作者: 堅毅 時間: 2025-3-23 12:12 作者: 多樣 時間: 2025-3-23 17:48 作者: 催眠 時間: 2025-3-23 19:14 作者: intrude 時間: 2025-3-23 23:18 作者: 外來 時間: 2025-3-24 05:57 作者: muscle-fibers 時間: 2025-3-24 08:55 作者: HAIRY 時間: 2025-3-24 14:30 作者: 泥瓦匠 時間: 2025-3-24 16:41 作者: 斷斷續(xù)續(xù) 時間: 2025-3-24 21:12 作者: nettle 時間: 2025-3-24 23:24
SE-GCN: A Syntactic Information Enhanced Model for Aspect-Based Sentiment Analysisnt years is mainly based on graph convolutional networks, and although much progress has been made, the existing methods focus on utilizing sequence information or syntactic dependency constraints within the text, but without fully utilizing the type of dependency relationships between the aspect te作者: 膝蓋 時間: 2025-3-25 05:16
CGSL: Collaborative Graph and?Segment Learning Based Aspect-Level Sentiment Analysis Modelsentiment analysis focuses on mining the grammatical and semantic relationship between aspects and isolated sentences. However, the relationship between words and multiple sentence contexts in the whole corpus and the sentiment attributes of different segments are ignored. We propose a collaborative作者: hypertension 時間: 2025-3-25 08:37 作者: 不出名 時間: 2025-3-25 12:11
SE-GCN: A Syntactic Information Enhanced Model for Aspect-Based Sentiment Analysisnt years is mainly based on graph convolutional networks, and although much progress has been made, the existing methods focus on utilizing sequence information or syntactic dependency constraints within the text, but without fully utilizing the type of dependency relationships between the aspect te作者: Fibrin 時間: 2025-3-25 17:07
Answering Spatial Commonsense Questions Based on?Chain-of-Thought Reasoning with?Adaptive ComplexityCurrent mainstream methods are based on the large language model (.) which uses the chain-of-thought (.) to support reasoning. However, these methods neglect to consider the differences in reasoning complexity of the questions when designing the . prompts, resulting in poor performance. Spatial ques作者: 庇護(hù) 時間: 2025-3-25 20:53 作者: Shuttle 時間: 2025-3-26 02:19
LLM-Based Empathetic Response Through Psychologist-Agent Debate in generating empathetic responses. But currently, many research only use a single LLM to generate responses. For empathetic responses, the approach of using a single LLM with single-turn has a problem, which is the lack of utilizing the capability of multiple LLMs for debate. Just like humans, the作者: 褲子 時間: 2025-3-26 07:47 作者: 男學(xué)院 時間: 2025-3-26 09:06
UFI4ER: An Utterance-Level Feature Dynamic Interaction Model for?Cognition-Enhanced Empathetic Respotead, they naturally engage in dynamic interactions throughout the conversation, facilitating the emergence and development of empathy. However, existing works primarily focus on capturing dialogue-level features, disregarding the sequential structure of dialogues and failing to perceive the dynamic作者: Jacket 時間: 2025-3-26 12:42
LLM-Based Empathetic Response Through Psychologist-Agent Debate in generating empathetic responses. But currently, many research only use a single LLM to generate responses. For empathetic responses, the approach of using a single LLM with single-turn has a problem, which is the lack of utilizing the capability of multiple LLMs for debate. Just like humans, the作者: 真實的人 時間: 2025-3-26 19:53
UFI4ER: An Utterance-Level Feature Dynamic Interaction Model for?Cognition-Enhanced Empathetic Respotead, they naturally engage in dynamic interactions throughout the conversation, facilitating the emergence and development of empathy. However, existing works primarily focus on capturing dialogue-level features, disregarding the sequential structure of dialogues and failing to perceive the dynamic作者: Medicare 時間: 2025-3-27 00:52
Enhancing Continual Relation Extraction with?Concept Aware Dynamic Memory Optimizationing works often rely on storing and replaying a fixed set of typical samples to prevent catastrophic forgetting. However, repeatedly replaying these samples may cause the biased latent features problem. In this paper, we find that the representations of memory samples will gradually lose representat作者: Acquired 時間: 2025-3-27 01:57 作者: modifier 時間: 2025-3-27 09:21
Knowledge-Enhanced Context Representation for?Unbiased Scene Graph Generationhips within a given image and to generate a structured representation of the scene. In order to enhance the model’s cognitive understanding of knowledge associations, this paper proposes a Knowledge-Enhanced Context Representation for Unbiased Scene Graph Generation model. To enhance the model, two 作者: 和平主義者 時間: 2025-3-27 09:32
Knowledge-Enhanced Context Representation for?Unbiased Scene Graph Generationhips within a given image and to generate a structured representation of the scene. In order to enhance the model’s cognitive understanding of knowledge associations, this paper proposes a Knowledge-Enhanced Context Representation for Unbiased Scene Graph Generation model. To enhance the model, two 作者: 好忠告人 時間: 2025-3-27 14:54 作者: Influx 時間: 2025-3-27 20:33
Enhancing NER with?Sentence-Level Entity Detection as?an?Simple Auxiliary Task model performance but also represents good generalization over multiple NER datasets. Our experiments on the MSRA and Weibo NER datasets show that our method could effectively boost the existing state-of-the-art NER methods, offering a compelling avenue for the advancement of efficient and robust NER methods.作者: 不易燃 時間: 2025-3-28 01:50
External Knowledge Enhancing Meta-learning Framework for?Few-Shot Text Classification via?Contrastivamples and their class prototypes. Furthermore, this paper employs an adversarial network to enhance the model’s generalization performance. The experiments show that the SCLAWM model has achieved remarkable performance on four benchmark datasets.作者: dominant 時間: 2025-3-28 04:08
Enhancing NER with?Sentence-Level Entity Detection as?an?Simple Auxiliary Task model performance but also represents good generalization over multiple NER datasets. Our experiments on the MSRA and Weibo NER datasets show that our method could effectively boost the existing state-of-the-art NER methods, offering a compelling avenue for the advancement of efficient and robust NER methods.作者: 裂隙 時間: 2025-3-28 07:52
External Knowledge Enhancing Meta-learning Framework for?Few-Shot Text Classification via?Contrastivamples and their class prototypes. Furthermore, this paper employs an adversarial network to enhance the model’s generalization performance. The experiments show that the SCLAWM model has achieved remarkable performance on four benchmark datasets.作者: 溫和女孩 時間: 2025-3-28 12:07 作者: 四溢 時間: 2025-3-28 16:01 作者: INTER 時間: 2025-3-28 22:38
0302-9743 e on Web and Big Data, APWeb-WAIM 2024, held in Jinhua, China, during August 30–September 1, 2024...The 171 full papers presented in these proceedings were carefully reviewed and selected from 558 submissions...The papers are organized in the following topical sections:.Part I:?Natural language proc作者: 使顯得不重要 時間: 2025-3-28 23:24 作者: 臭了生氣 時間: 2025-3-29 03:28 作者: Defense 時間: 2025-3-29 09:34
A Boundary Feature Enhanced Span-Based Nested Named Entity Recognition Method, to improve the efficiency of BFSN2ER, we introduce a multi-task learning framework to achieve jointly models training. To validate the performance of BFSN2ER, experiments were conducted on three large datasets. Comparing with seven baselines, BFSN2ER?achieved obviously better recall and F1-score, 作者: NAVEN 時間: 2025-3-29 11:33 作者: Lineage 時間: 2025-3-29 18:03
CeER: A Nested Name Entity Recognition Model Incorporating Gaze Features which reflect their importance in the reading cognitive process. Finally, we utilize the encoder improved by gaze feature learning and follow the question-answering architecture to identify all possible nested entities. We select three public eye-tracking datasets and two nested NER datasets, GENI作者: 共同時代 時間: 2025-3-29 22:10
Joint Semantic Relation Extraction for Multiple Entity Packetsng the fluctuations and regular semantics of entities. Finally, we aggregate the joint willingness among the entities in packets by combining the above two types of features, and thus extract the joint semantic relations effectively. Experimental results on various datasets illustrate that our metho作者: reject 時間: 2025-3-30 00:11 作者: Middle-Ear 時間: 2025-3-30 05:13
Explicit Relation-Enhanced AMR for?Document-Level Event Argument Extraction with?Global-Local Attentles and trigger interaction. This module also improves the model’s efficiency in resource allocation and enables a more refined focus on relational data, which optimizes performance in event argument extraction. Empirical evidence from experiments conducted on WIKIEVENTS shows that our model, enhanc作者: 駕駛 時間: 2025-3-30 10:58
Joint Semantic Relation Extraction for Multiple Entity Packetsng the fluctuations and regular semantics of entities. Finally, we aggregate the joint willingness among the entities in packets by combining the above two types of features, and thus extract the joint semantic relations effectively. Experimental results on various datasets illustrate that our metho作者: Bureaucracy 時間: 2025-3-30 13:17 作者: 清真寺 時間: 2025-3-30 16:56 作者: confederacy 時間: 2025-3-30 20:42
CGSL: Collaborative Graph and?Segment Learning Based Aspect-Level Sentiment Analysis Modeldel, simulation agent judgment, and strategy gradient method optimization to improve the performance. Finally, the output of the collaborative graph interaction component and segment learning component is integrated with the output of the attention mechanism as the final output of the proposed model作者: 侵害 時間: 2025-3-31 04:46
Parallel Program Generation for?Hybrid Tabular-Textual Question Answering setting these commendable benchmarks, our method facilitates a striking acceleration in program creation, achieving speeds nearly 21 times faster. Additionally, a salient feature of our approach becomes evident when numerical reasoning steps escalate: unlike traditional models, our system sustains 作者: 努力趕上 時間: 2025-3-31 05:40 作者: JAUNT 時間: 2025-3-31 10:30
CGSL: Collaborative Graph and?Segment Learning Based Aspect-Level Sentiment Analysis Modeldel, simulation agent judgment, and strategy gradient method optimization to improve the performance. Finally, the output of the collaborative graph interaction component and segment learning component is integrated with the output of the attention mechanism as the final output of the proposed model作者: Ligneous 時間: 2025-3-31 15:27 作者: lethal 時間: 2025-3-31 20:42
SE-GCN: A Syntactic Information Enhanced Model for Aspect-Based Sentiment Analysisgorithm is also proposed to establish connections between multi-word aspect terms and related viewpoint terms to increase the effective sense field in the convolution process. Experiments on four public datasets demonstrate the effectiveness of the proposed model.作者: 確認(rèn) 時間: 2025-4-1 00:24 作者: 耕種 時間: 2025-4-1 05:11
Similarity Retrieval and?Medical Cross-Modal Attention Based Medical Report Generationon Network (SRMCAN). By employing content-based similarity retrieval, SRMCAN filters out interfering information in relevant semantic features, which serves as?a complementary feature for the model. SRMCAN constructs a fine-grained alignment loss function, taking similar cases as hard negative sampl作者: 古代 時間: 2025-4-1 08:21
LLM-Based Empathetic Response Through Psychologist-Agent Debater empathetic responses is the lack of integration of different schools of psychology and multiple rounds. To address this issue, we propose a psychologist-agent-based multi-turn dialogue framework. This framework comprises a group of arguers with preferences of different psychological schools, used 作者: 連接 時間: 2025-4-1 14:12 作者: 構(gòu)想 時間: 2025-4-1 18:11 作者: Painstaking 時間: 2025-4-1 22:23
LLM-Based Empathetic Response Through Psychologist-Agent Debater empathetic responses is the lack of integration of different schools of psychology and multiple rounds. To address this issue, we propose a psychologist-agent-based multi-turn dialogue framework. This framework comprises a group of arguers with preferences of different psychological schools, used 作者: watertight, 時間: 2025-4-2 02:41 作者: FLORA 時間: 2025-4-2 04:54
Enhancing Continual Relation Extraction with?Concept Aware Dynamic Memory Optimizationappropriate training samples for replay training and the latter generates more accurate relation prototypes for the prediction. Our experimental results demonstrate the effectiveness of our method in mitigating biased feature representations to overcome catastrophic forgetting.作者: 領(lǐng)袖氣質(zhì) 時間: 2025-4-2 10:28
Enhancing Continual Relation Extraction with?Concept Aware Dynamic Memory Optimizationappropriate training samples for replay training and the latter generates more accurate relation prototypes for the prediction. Our experimental results demonstrate the effectiveness of our method in mitigating biased feature representations to overcome catastrophic forgetting.作者: Arable 時間: 2025-4-2 11:20
Knowledge-Enhanced Context Representation for?Unbiased Scene Graph Generationco-occurrence frequencies of entities and relationships, the global semantic representation of the entire image, and visual features are combined as inputs to generate contextual semantic representations for relational triplets. Additionally, this model also demonstrates improvement in addressing th作者: GOAD 時間: 2025-4-2 15:52
Knowledge-Enhanced Context Representation for?Unbiased Scene Graph Generationco-occurrence frequencies of entities and relationships, the global semantic representation of the entire image, and visual features are combined as inputs to generate contextual semantic representations for relational triplets. Additionally, this model also demonstrates improvement in addressing th作者: tattle 時間: 2025-4-2 20:20
Chen Wang,Cong Hu,Jiang Zhong,Huawen Liu,Qi Li,Donghua Yu,Xue Li作者: Absenteeism 時間: 2025-4-3 00:17 作者: 滲入 時間: 2025-4-3 06:45
Haoxiang Shi,Jianzong Wang,Xulong Zhang,Ning Cheng,Jun Yu,Jing Xiao作者: concise 時間: 2025-4-3 09:49
Wenke Yang,Zihan Yang,Liuyi Chen,Ruiqing Yan,Zhengyi Yang,Linhan Zhang,Yifu Tang作者: Ingratiate 時間: 2025-4-3 13:43
