检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

345 篇 期刊文献
328 篇 会议
16 册 图书
4 篇 学位论文

馆藏范围

693 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

504 篇 工学
- 445 篇 计算机科学与技术...
- 238 篇 软件工程
- 60 篇 信息与通信工程
- 50 篇 控制科学与工程
- 21 篇 电气工程
- 17 篇 农业工程
- 16 篇 机械工程
- 13 篇 化学工程与技术
- 10 篇 光学工程
- 10 篇 电子科学与技术（可...
- 9 篇 动力工程及工程热...
- 9 篇 生物医学工程（可授...
283 篇 理学
- 195 篇 数学
- 67 篇 物理学
- 61 篇 统计学（可授理学、...
- 31 篇 生物学
- 22 篇 系统科学
- 21 篇 科学技术史(分学科...
- 11 篇 化学
83 篇 管理学
- 60 篇 图书情报与档案管...
- 25 篇 管理科学与工程(可...
- 19 篇 工商管理
41 篇 哲学
- 26 篇 哲学
23 篇 法学
- 23 篇 社会学
20 篇 文学
- 20 篇 外国语言文学
- 18 篇 中国语言文学
19 篇 医学
- 16 篇 基础医学(可授医学...
- 16 篇 临床医学
18 篇 农学
- 17 篇 作物学
14 篇 教育学
- 11 篇 心理学(可授教育学...
5 篇 历史学
5 篇 艺术学
4 篇 经济学
1 篇 军事学

主题

59 篇 semantics
24 篇 computer circuit...
13 篇 computational li...
12 篇 game theory
10 篇 computational co...
10 篇 syntactics
10 篇 artificial intel...
9 篇 formal logic
9 篇 forestry
8 篇 quantum entangle...
8 篇 mathematical log...
8 篇 topology
8 篇 embeddings
7 篇 mathematical log...
7 篇 natural language...
7 篇 algorithm analys...
6 篇 logic
6 篇 discrete mathema...
6 篇 modal logic
6 篇 computation by a...

机构

351 篇 institute for lo...
31 篇 institute for lo...
22 篇 institute for lo...
13 篇 qusoft
13 篇 institute for lo...
12 篇 department of ma...
11 篇 institute of log...
9 篇 pacmed
7 篇 institut für mat...
7 篇 institute for lo...
6 篇 cwi
6 篇 institute for lo...
6 篇 institute for lo...
6 篇 university of am...
5 篇 institute for lo...
5 篇 informatics inst...
5 篇 amsterdam center...
5 篇 department of ph...
5 篇 institute for lo...
5 篇 department of ph...

作者

44 篇 fernández raquel
31 篇 zuidema willem
26 篇 walter michael
22 篇 endriss ulle
21 篇 venema yde
20 篇 sima'an khalil
19 篇 bezhanishvili ni...
19 篇 szymanik jakub
19 篇 van benthem joha...
16 篇 grossi davide
16 篇 pezzelle sandro
13 篇 löwe benedikt
12 篇 de haan ronald
11 篇 väänänen jouko
11 篇 cinà giovanni
11 篇 giulianelli mari...
10 篇 majenz christian
10 篇 ozols maris
10 篇 bod rens
10 篇 smets sonja

语言

663 篇 英文
29 篇 其他
1 篇 中文

检索条件"机构=Institute for Logic Language and Computation"

共 693 条记录，以下是1-10 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Modal Automata: Analysing Modal Fixpoint logics, One Step at a Time 33

Modal Automata: Analysing Modal Fixpoint Logics, One Step at...

引用

33rd EACSL Annual Conference on Computer Science logic, CSL 2025

作者： Venema, Yde Institute for Logic Language and Computation Universiteit van Amsterdam Netherlands

ISBN: (纸本)9783959773621

We present and investigate a general framework for studying modal fixpoint logics and some related versions of monadic second-order logic, by means of certain finite automata that operate on Kripke structures. Characteristic of these modal automata is that the co-domain of their transition function is a set of formulas of a so-called one-step logic. The motivation for taking this perspective is that if a logic is characterised by a class of modal automata, many of its properties are already determined at the level of the much simpler one-step logic. © Yde Venema.

关键词： Computer circuits

来源：评论

学校读者我要写书评

暂无评论

Breaking the Cycle Preference-Based Aggregation for Cyclic Argumentation Frameworks

Breaking the Cycle Preference-Based Aggregation for Cyclic A...

引用

2024 International Conference on computational Models of Argument, COMMA 2024

作者： Müller, Michael A. Istenič Urh, Blaž Zotescu, Teodor-Stefan Endriss, Ulle Institute for Logic Language and Computation University of Amsterdam Netherlands

ISBN: (纸本)9781643685342

We consider scenarios where a group of agents wish to simplify a given abstract argumentation framework-specifying a set of arguments and the attacks between them-by eliminating cycles in the attack-relation on the basis of their preferences over arguments. They do so by first aggregating their individual preferences into a collective preference order and then removing any attacks involved in a cycle that go against that order. Our analysis integrates insights from formal argumentation and social choice theory. We obtain sweeping impossibility results for essentially all standard methods of preference aggregation, showing that no Condorcet method and no positional scoring rule can uphold the fundamental principle expressing that views held by every single member of the group must be respected. But we also find that so-called representative-agent rules do offer this guarantee. © 2024 The Authors.

关键词： abstract argumentation preference aggregation preference-based argumentation social choice theory

来源：评论

学校读者我要写书评

暂无评论

Not (yet) the whole story: Evaluating Visual Storytelling Requires More than Measuring Coherence, Grounding, and Repetition

Not (yet) the whole story: Evaluating Visual Storytelling Re...

引用

2024 Conference on Empirical Methods in Natural language Processing, EMNLP 2024

作者： Surikuchi, Aditya K. Fernández, Raquel Pezzelle, Sandro Institute for Logic Language and Computation University of Amsterdam Netherlands

ISBN: (纸本)9798891761681

Visual storytelling consists in generating a natural language story given a temporally ordered sequence of images. This task is not only challenging for models, but also very difficult to evaluate with automatic metrics since there is no consensus about what makes a story 'good'. In this paper, we introduce a novel method that measures story quality in terms of human likeness regarding three key aspects highlighted in previous work: visual grounding, coherence, and repetitiveness. We then use this method to evaluate the stories generated by several models, showing that the foundation model LLaVA obtains the best result, but only slightly so compared to TAPM, a 50-times smaller visual storytelling model. Upgrading the visual and language components of TAPM results in a model that yields competitive performance with a relatively low number of parameters. Finally, we carry out a human evaluation study, whose results suggest that a 'good' story may require more than a human-like level of visual grounding, coherence, and repetition. © 2024 Association for computational Linguistics.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Automatic Animacy Classification for Romanian Nouns 30

Automatic Animacy Classification for Romanian Nouns

引用

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

作者： Tepei, Maria Bloem, Jelke Institute for Logic Language and Computation University of Amsterdam Netherlands

ISBN: (纸本)9782493814104

We introduce the first Romanian animacy classifier, specifically a type-based binary classifier of Romanian nouns into the classes human/non-human, using pre-trained word embeddings and animacy information derived from Romanian WordNet. By obtaining a seed set of labeled nouns and their embeddings, we are able to train classifiers that generalize to unseen nouns. We compare three different architectures and observe good performance on classifying word types. In addition, we manually annotate a small corpus for animacy to perform a token-based evaluation of Romanian animacy classification in a naturalistic setting, which reveals limitations of the type-based classification approach. © 2024 ELRA language Resource Association: CC BY-NC 4.0.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Continual Reinforcement Learning for Controlled Text Generation 30

Continual Reinforcement Learning for Controlled Text Generat...

引用

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

作者： Shulev, Velizar Sima'An, Khalil Institute for Logic Language and Computation University of Amsterdam Netherlands

ISBN: (纸本)9782493814104

Controlled Text Generation (CTG) steers the generation of continuations of a given context (prompt) by a Large language Model (LLM) towards texts possessing a given attribute (e.g., topic, sentiment). In this paper we view CTG as a Continual Learning problem: how to learn at every step to steer next-word generation, without having to wait for end-of-sentence. This continual view could be useful for online applications such as CTG for speech, where end-of-sentence is often uncertain. We depart from an existing model, the Plug-and-Play language models (PPLM), which perturbs the context at each step to better predict next-words that posses the desired attribute. While PPLM is intricate and has many hyper-parameters, we provide a proof that the PPLM objective function can be reduced to a Continual Reinforcement Learning (CRL) reward function, thereby simplifying PPLM and endowing it with a better understood learning framework. Subsequently, we present, the first of its kind, CTG algorithm that is fully based on CRL and exhibit promising empirical results. © 2024 ELRA language Resource Association: CC BY-NC 4.0.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

If I feel smart, I will do the right thing: Combining Complementary Multimodal Information in Visual language Models 1

If I feel smart, I will do the right thing: Combining Comple...

引用

1st Workshop of Evaluation of Multi-Modal Generation, EvalMG 2025

作者： Bai, Yuyu Pezzelle, Sandro Vrije Universiteit Amsterdam Netherlands Institute for Logic Language and Computation University of Amsterdam Netherlands

ISBN: (纸本)9798891762138

Generative visual language models (VLMs) have recently shown potential across various downstream language-and-vision tasks. At the same time, it is still an open question whether, and to what extent, these models can properly understand a multimodal context where language and vision provide complementary information—a mechanism routinely in place in human language communication. In this work, we test various VLMs on the task of generating action descriptions consistent with both an image’s visual content and an intention or attitude (not visually grounded) conveyed by a textual prompt. Our results show that BLIP-2 is not far from human performance when the task is framed as a generative multiple-choice problem, while other models struggle. Furthermore, the actions generated by BLIP-2 in an open-ended generative setting are better than those by the competitors;indeed, human annotators judge most of them as plausible continuations for the multimodal context. Our study reveals substantial variability among VLMs in integrating complementary multimodal information, yet BLIP-2 demonstrates promising trends across most evaluations, paving the way for seamless human-computer interaction. © 2025 Association for computational Linguistics.

关键词： computational linguistics

来源：评论

学校读者我要写书评

暂无评论

A Belief Model for Conflicting and Uncertain Evidence - Connecting Dempster-Shafer Theory and the Topology of Evidence 20

A Belief Model for Conflicting and Uncertain Evidence - Conn...

引用

20th International Conference on Principles of Knowledge Representation and Reasoning, KR 2023

作者： Prieto, Daira Pinto de Haan, Ronald Özgün, Aybüke Institute for Logic Language and Computation University of Amsterdam Netherlands

ISBN: (纸本)9781956792027

One problem to solve in the context of information fusion, decision-making, and other artificial intelligence challenges is to compute justified beliefs based on evidence. In real-life examples, this evidence may be inconsistent, incomplete, or uncertain, making the problem of evidence fusion highly nontrivial. In this paper, we propose a new model for measuring degrees of beliefs based on possibly inconsistent, incomplete, and uncertain evidence, by combining tools from Dempster-Shafer Theory and Topological Models of Evidence. Our belief model is more general than the aforementioned approaches in two important ways: (1) it can reproduce them when appropriate constraints are imposed, and, more notably, (2) it is flexible enough to compute beliefs according to various standards that represent agents' evidential demands. The latter novelty allows the users of our model to employ it to compute an agent's (possibly) distinct degrees of belief, based on the same evidence, in situations when, e.g, the agent prioritizes avoiding false negatives and when it prioritizes avoiding false positives. Finally, we show that computing degrees of belief with this model is #P-complete in general. © 2023 Proceedings of the International Conference on Knowledge Representation and Reasoning. All rights reserved

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Disjunctions of Universal Modals and Conditionals 4th

Disjunctions of Universal Modals and Conditionals

引用

4th Tsinghua Interdisciplinary Workshop on logic, language, and Meaning, TLLM 2024

作者： McHugh, Dean Department of Philosophy and Institute for Logic Language and Computation University of Amsterdam Amsterdam Netherlands

ISBN: (纸本)9783031860539

This paper is concerned with disjunctions of universal modals, such as You have to clean your room or you have to walk the dog, and disjunctions of conditionals, such as If Alice dances, Charlie will dance, or if Bob dances, Charlie will dance. We aim to provide a uniform account of their surprising behaviour. Our proposal combines three independently attested components. Firstly, disjunction’s dynamic effect, familiar from presupposition projection: when we evaluate a disjunction A∨B, we typically interpret B assuming the negation of A, and optionally, also interpret A assuming the negation of B. Secondly, the fact that disjunctions often receive a conjunctive interpretation, familiar from free choice phenomena. Thirdly, that modal bases are restricted to local contexts, what Mandelkern has called ‘bounded modality’. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Topic-guided Example Selection for Domain Adaptation in LLM-based Machine Translation 18

Topic-guided Example Selection for Domain Adaptation in LLM-...

引用

18th Conference of the European Chapter of the Association for computational Linguistics, EACL 2024 - Student Research Workshop, SRW 2024

作者： Aycock, Seth Bawden, Rachel Institute for Logic Language and Computation University of Amsterdam Netherlands Language Technology Lab. University of Amsterdam Netherlands Inria Paris France

ISBN: (纸本)9798891760905

Current machine translation (MT) systems perform well in the domains on which they were trained, but adaptation to unseen domains remains a challenge. Rather than fine-tuning on domain data or modifying the architecture for training, an alternative approach exploits large language models (LLMs), which are performant across NLP tasks especially when presented with in-context examples. We focus on adapting a pre-trained LLM to a domain at inference through in-context example selection. For MT, examples are usually randomly selected from a development set. Some more recent methods though select using the more intuitive basis of test source similarity. We employ topic models to select examples based on abstract semantic relationships below the level of a domain. We test the relevance of these statistical models and use them to select informative examples even for out-of-domain inputs, experimenting on 7 diverse domains and 11 language pairs of differing resourcedness. Our method outperforms baselines on challenging multilingual out-of-domain tests, though it does not match performance with strong baselines for the in-language setting. We find that adding few-shot examples and related keywords consistently improves translation quality, that example diversity must be balanced with source similarity, and that our pipeline is overly restrictive for example selection when a targeted development set is available. © 2024 Association for computational Linguistics.

关键词： Machine translation

来源：评论

学校读者我要写书评

暂无评论

Beyond Perplexity: Examining Temporal Generalization in Large language Models via Definition Generation 33

Beyond Perplexity: Examining Temporal Generalization in Larg...

引用

33rd Meeting of computational Linguistics in the Netherlands, CLIN 2023

作者： Luden, Iris Giulianelli, Mario Fernández, Raquel Institute for Logic Language and Computation University of Amsterdam Netherlands Department of Computer Science ETH Zürich Switzerland

The advent of large language models (LLMs) has significantly improved performance across various Natural language Processing tasks. However, the performance of LLMs has been shown to deteriorate over time, indicating a lack of temporal generalization. To date, performance deterioration of LLMs is primarily attributed to the factual changes in the real world over time. However, not only the facts of the world, but also the language we use to describe it constantly changes. Recent studies have indicated a relationship between performance deterioration and semantic change. This is typically measured using perplexity scores and relative performance on downstream tasks. Yet, perplexity and accuracy do not explain the effects of temporally shifted data on LLMs in practice. In this work, we propose to assess lexico-semantic temporal generalization of a language model by exploiting the task of contextualized word definition generation. This in-depth semantic assessment enables interpretable insights into the possible mistakes a model may perpetrate due to meaning shift, and can be used to complement more coarse-grained measures like perplexity scores. To assess how semantic change impacts performance, we design the task by differentiating between semantically stable, changing, and emerging target words, and experiment with T5-base, fine-tuned for contextualized definition generation. Our results indicate that (i) the model’s performance deteriorates for the task of contextualized word definition generation, (ii) the performance deteriorates more for semantically changing words compared to semantically stable words, (iii) the model exhibits significantly lower performance and potential bias for emerging words, and (iv) the performance does not correlate with cross-entropy or (pseudo)-perplexity scores.1 Overall, our results show that definition generation can be a promising task to assess a model’s capacity for temporal generalization with respect to semantic change. © 2024

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共70页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：