標(biāo)題: Titlebook: Natural Language Processing and Chinese Computing; 13th National CCF Co Derek F. Wong,Zhongyu Wei,Muyun Yang Conference proceedings 2025 Th [打印本頁(yè)] 作者: 威風(fēng) 時(shí)間: 2025-3-21 18:36
書(shū)目名稱Natural Language Processing and Chinese Computing影響因子(影響力)
書(shū)目名稱Natural Language Processing and Chinese Computing影響因子(影響力)學(xué)科排名
書(shū)目名稱Natural Language Processing and Chinese Computing網(wǎng)絡(luò)公開(kāi)度
書(shū)目名稱Natural Language Processing and Chinese Computing網(wǎng)絡(luò)公開(kāi)度學(xué)科排名
書(shū)目名稱Natural Language Processing and Chinese Computing被引頻次
書(shū)目名稱Natural Language Processing and Chinese Computing被引頻次學(xué)科排名
書(shū)目名稱Natural Language Processing and Chinese Computing年度引用
書(shū)目名稱Natural Language Processing and Chinese Computing年度引用學(xué)科排名
書(shū)目名稱Natural Language Processing and Chinese Computing讀者反饋
書(shū)目名稱Natural Language Processing and Chinese Computing讀者反饋學(xué)科排名
作者: GLADE 時(shí)間: 2025-3-21 23:13
https://doi.org/10.1007/978-981-97-9431-7Information extraction; Machine translation; Discourse, dialogue and pragmatics; Natural language gener作者: amphibian 時(shí)間: 2025-3-22 04:21 作者: MIRTH 時(shí)間: 2025-3-22 08:39 作者: ellagic-acid 時(shí)間: 2025-3-22 09:55 作者: 串通 時(shí)間: 2025-3-22 13:30
Learning to?Generate Style-Specific Adapters for?Stylized Dialogue Generatione systems. However, a major challenge to this task is the paucity of supervised data, resulting in suboptimal performance. Although some unsupervised methods have emerged, they tend to handle only a limited range of dialogue styles simultaneously. Retraining becomes necessary when new dialogue style作者: 車(chē)床 時(shí)間: 2025-3-22 18:34 作者: 裹住 時(shí)間: 2025-3-22 21:45
Multi-hop Reading Comprehension Model Based on?Abstract Meaning Representation and?Multi-task Joint ing supporting facts from multiple paragraphs in the document and reasoning to get the answer. But some problems have not been well solved: during the process of extracting the answer, it is often disturbed by the non-real answer (i.e. similar answer) in the document; the lack of a related expressio作者: 蹣跚 時(shí)間: 2025-3-23 03:56
Leveraging Large Language Models for?QA Dialogue Dataset Construction and?Analysis in?Public ServiceI) context. Existing datasets often lack the necessary interactive features for effective and efficient interactions, hindering the development of customized and emotionally responsive systems. As public service demands become more diverse and complex in HRI, traditional datasets fail to support hig作者: ENNUI 時(shí)間: 2025-3-23 07:40 作者: 小官 時(shí)間: 2025-3-23 11:01 作者: 牛的細(xì)微差別 時(shí)間: 2025-3-23 16:28
PqE: Zero-Shot Document Expansion for?Dense Retrieval with?Large Language Modelsual-encoder structure. Addressing this limitation, we introduce Pseudo-query Embedding (PqE), a document expansion approach that eliminates the need for supervised data. By zero-shot prompting large language models (LLMs), we generate a specific number of pseudo-queries for each document, which are 作者: 比喻好 時(shí)間: 2025-3-23 18:04
CKF: Conditional Knowledge Fusion Method for?CommonSense Question AnsweringIn the knowledge fusion process, existing KG-augmented methods ignore (i) . and (ii) .. As a result, the noise of KG cannot be filtered effectively in the knowledge fusion process. In this paper, we propose a .onditional .nowledge .usion method (CKF) (.). to enhance the commonsense reasoning ability作者: forecast 時(shí)間: 2025-3-23 23:14 作者: SPALL 時(shí)間: 2025-3-24 05:35 作者: 使饑餓 時(shí)間: 2025-3-24 08:44
Local or?Global Optimization for?Dialogue Discourse Parsingrevious studies either adopt local optimization to independently select one parent for each utterance or use global optimization to directly get the tree representing the dialogue structure. However, the influence of these two optimization methods remains less explored. In this paper, we aim to syst作者: MINT 時(shí)間: 2025-3-24 13:22 作者: 裹住 時(shí)間: 2025-3-24 17:59
Enhancing Emotional Support Conversation with?Cognitive Chain-of-Thought Reasoningrface utterance in conversation, making it difficult to understand the seeker’s deep status and provide effective emotional support through mere dialogue modeling. To address this challenge, we propose CogChain, a cognitive chain-of-thought (CoT) reasoning framework that mimics a human supporter’s c作者: 侵略者 時(shí)間: 2025-3-24 19:35 作者: guzzle 時(shí)間: 2025-3-24 23:21 作者: triptans 時(shí)間: 2025-3-25 04:10
PAPER: A Persona-Aware Chain-of-Thought Learning Framework for?Personalized Dialogue Response Genera and comprehend persona, especially when confronted with persona tags that have unique and obscure meanings, presenting barriers to generating a consistent response. Besides, previous studies have not fully utilized the rich persona information implied in the dialogue history. In this paper, we prop作者: 把手 時(shí)間: 2025-3-25 07:52
Towards Building a?Robust Knowledge Intensive Question Answering Model with?Large Language Modelsled models to better utilize external information. However, the presence of noise and errors in retrieved information poses challenges to the robustness of LLMs. In this work, to evaluate the model’s performance under multiple interferences, we first construct a dataset based on machine reading comp作者: 流逝 時(shí)間: 2025-3-25 12:31 作者: 過(guò)份艷麗 時(shí)間: 2025-3-25 17:52 作者: 折磨 時(shí)間: 2025-3-25 20:30 作者: 感情 時(shí)間: 2025-3-26 00:50
Peiyu Zhao,Zhujian Zhang,Bo Liu more. One of the most well-known disorders is liver cancer. Liver cancer causes major loss to human lives. Early detection of this can be curable at the initial stages. Due to the advancement of computer vision algorithms and progression of IoT technologies working along with image processing techn作者: 刺穿 時(shí)間: 2025-3-26 05:09
Chaomin Wu,Di Wu,Yushan Pan,Hao Wangealthcare technology towards a phenomenal development. Healthcare has entered the digital era as a process driven by need. With access to large amounts of medical information from healthcare specialities, technologies, and electronic health records, its usability to improve the healthcare processes 作者: 絕種 時(shí)間: 2025-3-26 12:09 作者: Innovative 時(shí)間: 2025-3-26 12:46
Meiwen Li,Tianyu Cai,Lingyan Wu,Li Chen,Shenggen Jurldwide.Discusses specific methods which have made CEDAW res.This book looks at the centerpiece of the international women’s rights discourse, the Convention on the Elimination of all Forms of Discrimination against Women (CEDAW), and asks to what extent it affects the lives of women worldwide. Rath作者: 審問(wèn) 時(shí)間: 2025-3-26 18:27
Jiyuan Liu,Dongsheng Zou,Naiquan Chai,Yuming Yang,Hao Wang,Xinyi Songrldwide.Discusses specific methods which have made CEDAW res.This book looks at the centerpiece of the international women’s rights discourse, the Convention on the Elimination of all Forms of Discrimination against Women (CEDAW), and asks to what extent it affects the lives of women worldwide. Rath作者: Cabg318 時(shí)間: 2025-3-27 00:00 作者: Constituent 時(shí)間: 2025-3-27 04:35
Bihan Zhou,Haopeng Ren,Yi Cai,Zetao Lian,Pinli Zhu,Yushi Zengy drawn between ‘the West‘ and ‘the Rest of the World’.Goes This book provides the first full-length, English-language investigation of the multiple and often contradictory ways in which mothers who kill their children were portrayed in 1970s Japan. It offers a snapshot of a historical and social mo作者: 欺騙手段 時(shí)間: 2025-3-27 06:02 作者: Figate 時(shí)間: 2025-3-27 12:22 作者: Override 時(shí)間: 2025-3-27 15:03
Rui Cao,Xiabing Zhou,Guodong Zhouon. The novel is set at the end of the 1990s and beginning of the 21st century. It brings onto stage characters directly linked to the economic migrations that took place in the late 1950s until around the 1970s from Spain to France. Through these characters, a kind of sociolect of the migrant is co作者: 統(tǒng)治人類(lèi) 時(shí)間: 2025-3-27 21:23
Yaru Cao,Zhuang Chen,Guanqun Bi,Yulin Feng,Min Chen,Fucheng Wan,Minlie Huang,Hongzhi Yund in relation to the socio-political context that frames it, this article analyses the (re)translations of Virginia Woolf ’s A Room of One’s Own and Three Guineas – which appeared during and after Franco’s dictatorship. The focus is put on how the translators’ choices of grammatical gender affect f作者: chronicle 時(shí)間: 2025-3-28 01:42 作者: 季雨 時(shí)間: 2025-3-28 03:48 作者: myocardium 時(shí)間: 2025-3-28 06:32 作者: Foolproof 時(shí)間: 2025-3-28 12:40 作者: 聽(tīng)寫(xiě) 時(shí)間: 2025-3-28 14:40 作者: 危險(xiǎn) 時(shí)間: 2025-3-28 21:34 作者: 歡樂(lè)中國(guó) 時(shí)間: 2025-3-28 23:11
Hierarchical Knowledge Aggregation for Personalized Response Generation in Dialogue Systemsition task to enhance the accurate modeling of structural information. The results of our experiments, conducted on the ConvAI2 and PersonalDialog datasets, demonstrate that HKA outperforms existing baselines in generating personalized responses.作者: 向外 時(shí)間: 2025-3-29 04:47 作者: 尖 時(shí)間: 2025-3-29 09:22
Conference proceedings 2025inese Computing, NLPCC 2024, held in Hangzhou, China,?during?November 2024...The 161 full papers and 33 evaluation workshop papers included in these proceedings were carefully reviewed and selected from 451 submissions. They deal with the following areas: Fundamentals of?NLP; Information Extraction 作者: 記成螞蟻 時(shí)間: 2025-3-29 12:50 作者: 危險(xiǎn) 時(shí)間: 2025-3-29 18:51
CKF: Conditional Knowledge Fusion Method for?CommonSense Question Answeringnd, we design a conditional fusion module to .. To further improve performance, we design a re-attention mechanism to supplement PLM with commonsense knowledge. Experimental results demonstrate the superior effectiveness of CKF through considerable performance gains across three popular benchmark datasets.作者: gentle 時(shí)間: 2025-3-29 22:59 作者: 證實(shí) 時(shí)間: 2025-3-30 01:01
Learning to?Generate Style-Specific Adapters for?Stylized Dialogue Generationle-specific adapters for modeling both contexts and stylized responses. These style-specific adapters are generated by a hypernetwork trained on multiple stylized corpora. In addition, for unseen stylized texts, MultiSADG uses the stylized corpus to generate style-specific adapters through the hyper作者: sultry 時(shí)間: 2025-3-30 08:01 作者: 有助于 時(shí)間: 2025-3-30 09:37 作者: CRAB 時(shí)間: 2025-3-30 13:41
MCFC: A Momentum-Driven Clicked Feature Compressed Pre-trained Language Model for?Information Retries and compress the dispersed knowledge together at the query granularity, named Multi-Instance Information Integration. Meanwhile, more relevant detection between queries and documents is eager in coarse clicked data background, we leverage a momentum-driven adjusting mechanism to refine the text re作者: 膽大 時(shí)間: 2025-3-30 18:39
Integrating Syntax Tree and?Graph Neural Network for?Conversational Question Answering over?Heteroges and predicts node scores of the word nodes in the tree. This is based on the node’s entity information and its relevance to the current question within the neighborhood. A graph neural network that includes entity-level attention is used to complete the extraction of the question entities. Experim作者: Clumsy 時(shí)間: 2025-3-31 00:01
PqE: Zero-Shot Document Expansion for?Dense Retrieval with?Large Language Modelsecall@1k metric by 4% points, surpassing the performance of the BM25 algorithm. Even for contriever., fine-tuned on the massive dataset MS-MARCO, and BGE, trained on hundreds of millions of query-document pairs, PqE boosts their Recall@1k metrics on the TREC DL dataset by 1 to 2% points. Notably, on作者: Ablation 時(shí)間: 2025-3-31 03:31 作者: abysmal 時(shí)間: 2025-3-31 07:18 作者: IRATE 時(shí)間: 2025-3-31 11:11
Structure and?Behavior Dual-Graph Reasoning with?Integrated Key-Clue Parsing for?Multi-party Dialogut, which significantly reduces the burden on the model and enhances the accuracy of our model. The experiments on the benchmark dataset show that our approach yields stable and substantial improvements, and outperforms the state-of-the-art methods.作者: 笨拙的你 時(shí)間: 2025-3-31 15:22
Enhancing Emotional Support Conversation with?Cognitive Chain-of-Thought Reasoningrain enhanced machine supporters with CoT reasoning ability. Extensive automatic and human evaluations show that, CogChain not only improves the machine supporter’s performance for in-domain seen scenarios but also enhances its generalizability to out-of-domain unseen scenarios, demonstrating the im作者: Derogate 時(shí)間: 2025-3-31 20:10
A Simple and Effective Span Interaction Modeling Method for Enhancing Multiple Span Question Answeriments demonstrate that baselines, on MultiSpanQA, incorporating our strategy achieved an improvement in EM F1 ranging from 2.88 to 11.27, achieving state-of-the-art (SOTA) results at equivalent model scales.作者: 谷物 時(shí)間: 2025-3-31 23:17 作者: Communicate 時(shí)間: 2025-4-1 05:49 作者: Arable 時(shí)間: 2025-4-1 08:59
Towards Building a?Robust Knowledge Intensive Question Answering Model with?Large Language Modelsments on both existing LLMs and our approach, the results are evaluated by GPT-4, which indicates that our proposed methods improve model robustness while strengthening the model’s discrimination capability.作者: Anticoagulants 時(shí)間: 2025-4-1 13:05
Xingsheng Zhang,YiFan Deng,Yue Hu,Yunpeng Li,Ping Guouitable system architecture, data storage, handling and accessing systems, defining suitable protocols, framing policies and guidelines. Three important revolutions occurred in the twenty-first century which focus on internet, omics and artificial intelligence.
