检索结果-内蒙古大学图书馆

7th International Conference on Machine Learning and Natural language Processing, MLNLP 2024

作者： Luo, Yuhao Zhang, Zhengkun Zhang, Yao Xie, Zheng Wang, Jun Jatowt, Adam Yang, Zhenglu Nankai University TKLNDST CS China School of Statistics and Data Science Nankai University LPMC KLMDASR LEBPS China College of Mathematics and Statistics Science Ludong University Shandong Key Laboratory of Language Resource Development and Application China University of Innsbruck Austria

ISBN: (纸本)9798350354973

Event Argument Extraction (EAE) facilitates comprehension of the text related to an event by extracting and analyzing event arguments. The superiority of previous studies typically rises from the abundance of high-quality event annotations, which is labor-intensive to produce and hard to satisfy by reality. In this paper, we approach data-scarce EAE in both low-resource and few-shot scenarios, which have far-reaching implications for practice. Specifically, we propose a model called Dynamic Modular Prompt Tuning based on Slot-Transfer (DAMPT), which dispenses with any manual effort usually required in existing methods. DAMPT turns to large-scale language models to generate dynamic modular prompts, which are more adaptable than the static ones manually given by experts. Furthermore, DAMPT incorporates a prompt-tuning algorithm called slot-transfer to facilitate event-specific knowledge transfer. An extensive experimental evaluation validates the effectiveness and generalization ability of DAMPT in data-scarce scenarios. © 2024 IEEE.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Can We Learn Question, Answer, and Distractors All from An Image? A New Task for Multiple-Choice Visual Question Answering 30

Can We Learn Question, Answer, and Distractors All from An I...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on language resources and Evaluation, LREC-COLING 2024

作者： Ding, Wenjian Zhang, Yao Wang, Jun Jatowt, Adam Yang, Zhenglu TKLNDST CS Nankai University China School of Statistics and Data Science LPMC KLMDASR LEBPS Nankai University China Shandong Key Laboratory of Language Resource Development and Application College of Mathematics and Statistics Science Ludong University China University of Innsbruck Austria

ISBN: (纸本)9782493814104

Multiple-choice visual question answering (MC VQA) requires an answer picked from a list of distractors, based on a question and an image. This research has attracted wide interests from the fields of visual question answering, visual question generation, and visual distractor generation. However, these fields still stay in their own territories, and how to jointly generate meaningful questions, correct answers, and challenging distractors remains unexplored. In this paper, we introduce a novel task, Visual Question-Answer-Distractors Generation (VQADG), which can bridge this research gap as well as take as a cornerstone to promote existing VQA models. Specific to the VQADG task, we present a novel framework consisting of a vision-and-language model to encode the given image and generate QADs jointly, and contrastive learning to ensure the consistency of the generated question, answer, and distractors. Empirical evaluations on the benchmark dataset validate the performance of our model in the VQADG task. © 2024 ELRA language resource Association: CC BY-NC 4.0.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Data-Scarce Event Argument Extraction: A Dynamic Modular Prompt Tuning Model Based on Slot Transfer

Data-Scarce Event Argument Extraction: A Dynamic Modular Pro...

引用

Machine Learning and Natural language Processing (MLNLP), International Conference on

作者： Yuhao Luo Zhengkun Zhang Yao Zhang Zheng Xie Jun Wang Adam Jatowt Zhenglu Yang TKLNDST CS Nankai University LPMC KLMDASR & LEBPS School of Statistics and Data Science Nankai University Shandong Key Laboratory of Language Resource Development and Application College of Mathematics and Statistics Science Ludong University University of Innsbruck Austria

ISBN: (数字)9798350354973

ISBN: (纸本)9798350354980

关键词： Adaptation models Annotations Heuristic algorithms Manuals Machine learning Transformers Natural language processing Tuning Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

Well Begun is Half Done: Generator-agnostic Knowledge Pre-Selection for Knowledge-Grounded Dialogue

arXiv

引用

arXiv 2023年

作者： Qin, Lang Zhang, Yao Liang, Hongru Wang, Jun Yang, Zhenglu TKLNDST CS Nankai University China Key Laboratory of DISSec Ministry of Education China School of Statistics and Data Science LPMC KLMDASR & LEBPS Nankai University China College of Computer Science Sichuan University China College of Mathematics and Statistics Science Shandong Key Laboratory of Language Resource Development and Application Ludong University China Education Field Integrated & Publishing Knowledge Mining & Service Key Laboratory National Press and Publication Administration China

Accurate knowledge selection is critical in knowledge-grounded dialogue systems. Towards a closer look at it, we offer a novel perspective to organize existing literature, i.e., knowledge selection coupled with, after, and before generation. We focus on the third under-explored category of study, which can not only select knowledge accurately in advance, but has the advantage to reduce the learning, adjustment, and interpretation burden of subsequent response generation models, especially LLMs. We propose GATE, a generator-agnostic knowledge selection method, to prepare knowledge for subsequent response generation models by selecting context-related knowledge among different knowledge structures and variable knowledge requirements. Experimental results demonstrate the superiority of GATE, and indicate that knowledge selection before generation is a lightweight yet effective way to facilitate LLMs (e.g., ChatGPT) to generate more informative responses. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Multiple Feature Approach for Disorder Normalization in Clinical Notes

引用

Wuhan University Journal of Natural Sciences 2016年第6期21卷 482-490页

作者： Lü Chen CHEN Bo Lü Chaozhen QIU Likun JI Donghong School of Computer Wuhan University Department of Chinese Language and Literature Hubei University of Art and Science Shandong Key Lab of Language Resource Development and Application Ludong University

In this paper we propose a multiple feature approach for the normalization task which can map each disorder mention in the text to a unique unified medical language system（UMLS）concept unique identifier（CUI）. We develop a two-step method to acquire a list of candidate CUIs and their associated preferred names using UMLS API and to choose the closest CUI by calculating the similarity between the input disorder mention and each candidate. The similarity calculation step is formulated as a classification problem and multiple features（string features,ranking features,similarity features,and contextual features） are used to normalize the disorder mentions. The results show that the multiple feature approach improves the accuracy of the normalization task from 32.99% to 67.08% compared with the Meta Map baseline.

关键词： natural language processing disorder normalization Levenshtein distance semantic composition multiple features

来源：评论

学校读者我要写书评

暂无评论

Lexical-semantic constraints on the semantics-to-syntax projecting: A case study of location

引用

ICIC Express Letters, Part B: applications 2016年第7期7卷 1439-1444页

作者： Kang, Shiyong Zhou, Minghai Shi, Linlin Key Laboratory of Language Resource Development and Application of Shandong Province Ludong University No. 186 Middle Hongqi Road Zhifu District Yantai264025 China School of Chinese Language and Literature Ludong University No. 186 Middle Hongqi Road Zhifu District Yantai264025 China

The lexicon-to-syntax projecting is semantically constrained. This article exemplifies the semantic role Location, focusing on its morphological marker, syntactic components it can be projected as, the in uence of its subcategories on the projecting, and its semantic characteristics, based on a large-scale annotated corpus, and hence gives a preliminary illustration on how the semantic categories constrain the lexicon-to-syntax projecting. © 2016, ICIC Express Letters Office. All rights reserved.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Automatic extraction and quantitative analysis of Chinese separable words

引用

ICIC Express Letters 2016年第6期10卷 1511-1516页

作者： He, Baorong Qiu, Likun Key Laboratory of Language Resource Development and Application of Shandong Province Ludong University No. 186 Middle Hongqi Road Zhifu District Yantai264025 China School of Chinese Language and Literature Ludong University No. 186 Middle Hongqi Road Zhifu District Yantai264025 China

Chinese separable words is a research focus in Chinese linguistics and natural language processing. This paper proposed a method for extracting Chinese separable words both in their combined forms and separate forms. Based on the extracted results, we analyze unigram, bigram and trigram inserted elements and show that a multi-syllable inserted element usually composes two or more shorter ones. In addition, our analysis demonstrated that the separate degrees of separable words are quite different. © 2016 ISSN.

关键词： Separation

来源：评论

学校读者我要写书评

暂无评论

Research of automatically generate mapping mechanism based on the semantic role

International Journal of Database Theory and Application

引用

International Journal of Database Theory and application 2016年第10期9卷 163-176页

作者： Wang, Feng Cui, Lei Wang, Yizhen Wei, Xinjiang School of Mathematics and Statistics Science Ludong University Yan Tai264025 China Key Laboratory of Language Resource Development and Application of Shandong Province Yan Tai China Information Engineering Department Yan Tai Vocational College Yan Tai264025 China Tilburg University Tilburg Netherlands

Role based access control (RBAC) has been widely adopted in industrial and government. However RBAC is only suitable for closed enterprise environment. With modern Internet based application, collaboration and sharing among multiple organizations become essential and RBAC is no longer sufficient. Role mapping has been the solutions to deal with multiple domains, where the roles in the hierarchy of one organization are mapped to the roles in the hierarchy of another organization. But role mapping can be a tedious task for the security officers if it is done fully manually. Yet, performing role mapping automatically incur security risks. In this paper, we introduce a semi-automated role mapping process, where promising role mappings are generated automatically and recommended to the security officer(s). The security officers then approve or modify the recommended role mappings. We present a method for automatically generate role mappings based on the similarities of the roles in two role hierarchies. We use an example to illustrate our approach and show its feasibility. 2016 SERSC.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Research on intelligent semantic search base on HowNet

引用

Open Cybernetics and Systemics Journal 2015年第1期9卷 1358-1364页

作者： Wang, Feng Zhang, Hui Wang, Yizhen Zhang, Guanghua School of Mathermatics and Statistics Science Ludong University Yantai264025 China Key Laboratory of Language Resource Development and Application of Shandong Province Yantai264025 China College of Information Science and Engineering Hebei University of Science and Technology Shijiazhuang China Tilburg University Tilburg Netherlands

The HDWiki is same as the famous Wikipedia but major in Chinese include vase investment of manual effort and judgment, we divided this structured information into three categories: concept, relationship and entity. This paper describe a novel symbol oriented search that facilitate user to format unambiguous query, especially to format complex logical query which need several query to get answer on traditional search but just once here, it is building a bridge between what user know and what user wished, between the intent of user query and the understanding of search engine. This facilitation and understanding base on the ternary relationships what are everywhere in the HDWiki and HowNet powered semantic similarity measure for knowledge matching. We realize a logical semantic oriented search system and conducted a detailed user study with users, and found that this logical semantic oriented search and its underlying knowledge base provides significant advantages over conventional search. It offers assistance to almost every query especially complex logical queries, making the query entry more clear and efficient for user as well as for search engine, broadening the processing scope of complex logical query in the search, improving the relevance of the searched documents, and increased the probability of getting what user wished. © Wang et al.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

System of automatic Chinese webpage summarization based on the random walk algorithm of dynamic programming

引用

Open Cybernetics and Systemics Journal 2015年第1期9卷 1315-1322页

作者： Wang, Feng Qin, Xiaoming Wang, Yizhen Wei, Xinjiang School of Mathermatics and Statistics Science Ludong University Yantai264025 China Key Laboratory of Language Resource Development and Application of Shandong Province Yantai264025 China College of Computer and Information Engineering Jiaozuo Teachers College Jiaozuo454000 China Institute of Computer Application Technology Jiaozuo Teachers College Jiaozuo454000 China Tilburg University Tilburg Netherlands

As the Internet becomes more and more deeply connected with our life, the Internet has brought together mass text material, and it is still in explosive growth. In order to quickly and accurately to help users find the required content, the traditional solution is to use a search engine. However, the results of existing automatic webpage summarization systems for search engine are of low quality. Because they just based on statistical method, gather some sentences in the web document beside the search phrases. Neither symbolizes the subject of the document, nor take into account the user search phrases. According to the shortages, An automatic webpage summarization systems is realized. On the basis of the work done, this paper proposed an automatic text summarization method based on relation graph and text structure analysis. This method firstly segment text into semantic paragraphs. For each semantic paragraph, a subject term discover method based on relation graph analysis is proposed. At last, both search phrase and document subject are take into account, it extracts summary according to the guidance of the subject terms. © Wang et al.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：