检索结果-内蒙古大学图书馆

24th International Conference on Knowledge Engineering and Knowledge Management, EKAW 2024

作者： Schmidt, David Maria Elahi, Mohammad Fazleh Cimiano, Philipp Semantic Computing Group CITEC Technical Faculty Bielefeld University Bielefeld Germany

ISBN: (纸本)9783031777912

In this paper, we examine the impact of lexicalization on Question Answering over Linked Data (QALD). It is well known that one of the key challenges in interpreting natural language questions with respect to SPARQL lies in bridging the lexical gap, that is mapping the words in the query to the correct vocabulary elements. We argue in this paper that lexicalization, that is explicit knowledge about the potential interpretations of a word with respect to the given vocabulary, significantly eases the task and increases the performance of QA systems. Towards this goal, we present a compositional QA system that can leverage explicit lexical knowledge in a compositional manner to infer the meaning of a question in terms of a SPARQL query. We show that such a system, given lexical knowledge, has a performance well beyond current QA systems, achieving up to a 35.8% increase in the micro F1 score compared to the best QA system on QALD-9. This shows the importance and potential of including explicit lexical knowledge. In contrast, we show that LLMs have limited abilities to exploit lexical knowledge, with only marginal improvements compared to a version without lexical knowledge. This shows that LLMs have no ability to compositionally interpret a question on the basis of the meaning of its parts, a key feature of compositional approaches. Taken together, our work shows new avenues for QALD research, emphasizing the importance of lexicalization and compositionality. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

An Empirical Investigation of Users’ Assessment of XAI Explanations: Identifying the Sweet Spot of Explanation Complexity and Value 2

An Empirical Investigation of Users’ Assessment of XAI Expl...

引用

Joint of the 2nd World Conference on eXplainable Artificial Intelligence Late-Breaking Work, Demos and Doctoral Consortium, xAI-2024:LB/D/DC

作者： Liedeker, Felix Düsing, Christoph Nieveler, Marcel Cimiano, Philipp Semantic Computing Group CITEC Bielefeld University Inspiration 1 Bielefeld33619 Germany

While the importance of explainable artificial intelligence in high-stakes decision-making is widely recognized in existing literature, empirical studies assessing users’ perceived value of explanations are scarce. In this paper, we aim to address this shortcoming by conducting an empirical study focused on measuring the perceived value of the following types of explanations: plain explanations based on feature attribution, counterfactual explanations and complex counterfactual explanations. We measure an explanation’s value using five dimensions: perceived accuracy, understandability, plausibility, sufficiency of detail, and user satisfaction. Our findings indicate a sweet spot of explanation complexity, with both dimensional and structural complexity positively impacting the perceived value up to a certain threshold. © 2024 Copyright for this paper by its authors.

关键词： Counterfactual Explanation Explainable AI (XAI) Explanation Complexity User Perception

来源：评论

学校读者我要写书评

暂无评论

ASCODI: An XAI-based interactive reasoning support system for justifiable medical diagnosing 1

ASCODI: An XAI-based interactive reasoning support system fo...

引用

1st Multimodal, Affective and Interactive eXplainable AI Workshop, MAI-XAI24 2024

作者： Battefeld, Dominik Liedeker, Felix Cimiano, Philipp Kopp, Stefan Social Cognitive Systems Group CITEC Bielefeld University Inspiration 1 Bielefeld33619 Germany Semantic Computing Group CITEC Bielefeld University Inspiration 1 Bielefeld33619 Germany

Research has shown that approximately 10% of medical diagnoses are wrong. As a direct consequence, appropriate medical treatment may be delayed or even absent, leading to an increased burden on patients, increased costs for medication, or even harm and death. As cognitive biases contribute to roughly three-quarters of these diagnostic errors, a lot can be gained from increasing a physician’s reasoning quality during the diagnostic process. Clinical decision support systems (CDSS), leveraging recent advances in artificial intelligence (AI) and insights from eXplainable AI (XAI), aim at providing accurate predictions and prognosis paired with corresponding ex-post explanations that make the reasoning of the system accessible to humans. Viewing explanations as involving the interactive construction of shared belief, we propose to move from diagnostic decision support to reasoning support which, in its true sense, needs to tailor the timing and content of generated explanations to the state of the reasoning process of physicians to meet their information needs and effectively mitigate the influence of cognitive biases. We claim that, given the uncertain and incomplete information inherent to medical diagnosis, the most effective way not to fall prey to cognitive reasoning errors is to establish and maintain proper justification for each decision throughout the diagnostic process. This paper contributes (1) a conceptual model and desiderata for AI-based interactive reasoning support that enhances reasoning quality through increased justification at every stage of the process, and (2) preliminary work on the development of the assistive, co-constructive differential diagnosis system, ASCODI, which provides reactive as well as proactive reasoning support to improve the justification of actions taken and decisions made during and after medical diagnosing. We also present selected use cases of ASCODI concerning its application in supporting the diagnosis of transient loss of

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Lexicalization Is All You Need: Examining the Impact of Lexical Knowledge in a Compositional QALD System

arXiv

引用

arXiv 2024年

作者： Schmidt, David Maria Elahi, Mohammad Fazleh Cimiano, Philipp Semantic Computing Group CITEC Technical Faculty Bielefeld University Bielefeld Germany

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Generating grammars from lemon lexica for questions answering over linked data: A preliminary analysis

Generating grammars from lemon lexica for questions answerin...

引用

2020 Advances in semantics and Linked Data, ASLD 2020 and Joint Workshops AI4LEGAL 2020, NLIWOD, PROFILES 2020, QuWeDa 2020 and SEMIFORM 2020

作者： Benz, Viktoria Cimiano, Philipp Elahi, Mohammad Fazleh Ell, Basil Semantic Computing Group CITEC Universität Bielefeld Inspiration 1 Bielefeld33619 Germany

Most approaches to question answering over linked data (QALD) frame the task as a machine learning problem, consisting in learning a mapping from natural language questions into SPARQL queries by parametrizing a model from training data given in the form of pairs of natural language (NL) question and SPARQL query. In this preliminary work we present an alternative approach to developing a QA system using machine learning that relies on the automatic generation of a QA grammar from a lemon lexicon. This model-based approach comes with a number of advantages compared to a machine learning approach. First, our approach gives maximum control over the QA interface to the developer of the system as every entry added to the lexicon increases the coverage of the grammar and thus of the QA system in a predictable way. This is in contrast to machine learning approaches where the impact of the addition of a single training example is difficult to predict. A further advantage of our approach is that the QA system operates on the basis of a symbolic grammar that can be used to provide guidance and auto-completion functionality to users. Our system is indeed intended to be used in the context of an auto-completion interface that allows users to ask only questions that the grammar can cover. We present very preliminary results showing that a large percentage of the questions of the training set of QALD-7 can be rephrased in terms of questions that our grammar can parse. We show that with a hand-crafted lexicon, we can in principle get very high micro-F1 scores of 62.5% on the training data of QALD-7 when questions are manually rephrased to fit our grammar. Although these preliminary results do not constitute a proper evaluation of our approach, they hint at the fact that an approach as we propose seems feasible. Copyright © 2020 for this paper by its authors.

关键词： Linked data

来源：评论

学校读者我要写书评

暂无评论

Evaluating Architectural Choices for Deep Learning Approaches for Question Answering Over Knowledge Bases

Evaluating Architectural Choices for Deep Learning Approache...

引用

International Conference on semantic computing

作者： Sherzod Hakimov Soufian Jebbara Philipp Cimiano Semantic Computing Group CITEC Bielefeld University

The task of answering natural language questions over knowledge bases has received wide attention in recent years. Various deep learning architectures have been proposed for this task. However, architectural design choices are typically not systematically compared nor evaluated under the same conditions. In this paper, we contribute to a better understanding of the impact of architectural design choices by evaluating four different architectures under the same conditions. We address the task of answering simple questions, consisting in predicting the subject and predicate of a triple given a question. In order to provide a fair comparison of different architectures, we evaluate them under the same strategy for inferring the subject, and compare different architectures for inferring the predicate. The architecture for inferring the subject is based on a standard LSTM model trained to recognize the span of the subject in the question and on a linking component that links the subject span to an entity in the knowledge base. The architectures for predicate inference are based on i) a standard softmax classifier ranging over all predicates as output, ii) a model that predicts a low-dimensional encoding of the property and subject entity, iii) a model that learns to score a pair of subject and predicate given the question as well as iv) a model based on the well-known FastText model. The comparison of architectures shows that FastText provides better results than other architectures.

关键词： Predictive models Task analysis Computational modeling Computer architecture Indexes Training Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Zero-shot cross-lingual opinion target extraction

arXiv

引用

arXiv 2019年

作者： Jebbara, Soufian Cimiano, Philipp Semalytix GmbH Bielefeld Germany Semantic Computing Group CITEC - Bielefeld University Bielefeld Germany

Aspect-based sentiment analysis involves the recognition of so called opinion target expressions (OTEs). To automatically extract OTEs, supervised learning algorithms are usually employed which are trained on manually annotated corpora. The creation of these corpora is labor-intensive and sufficiently large datasets are therefore usually only available for a very narrow selection of languages and domains. In this work, we address the lack of available annotated data for specific languages by proposing a zero-shot cross-lingual approach for the extraction of opinion target expressions. We leverage multilingual word embeddings that share a common vector space across various languages and incorporate these into a convolutional neural network architecture for OTE extraction. Our experiments with 5 languages give promising results: We can successfully train a model on annotated data of a source language and perform accurate prediction on a target language without ever using any annotated samples in that target language. Depending on the source and target language pairs, we reach performances in a zero-shot regime of up to 77% of a model trained on target language data. Furthermore, we can increase this performance up to 87% of a baseline model trained on target language data by performing cross-lingual learning from multiple source languages. Copyright © 2019, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Question Answering on Knowledge Bases: an evaluation of architectural design choices

arXiv

引用

arXiv 2018年

作者： Hakimov, Sherzod Jebbara, Soufian Cimiano, Philipp Semantic Computing Group CITEC Bielefeld University

The task of answering natural language questions over knowledge bases has received wide attention in recent years. Various deep learning architectures have been proposed for this task. However, architectural design choices are typically not systematically compared nor evaluated under the same conditions. In this paper, we contribute to a better understanding of the impact of architectural design choices by evaluating four different architectures under the same conditions. We address the task of answering simple questions, consisting in predicting the subject and predicate of a triple given a question. In order to provide a fair comparison of different architectures, we evaluate them under the same strategy for inferring the subject, and compare different architectures for inferring the predicate. The architecture for inferring the subject is based on a standard LSTM model trained to recognize the span of the subject in the question and on a linking component that links the subject span to an entity in the knowledge base. The architectures for predicate inference are based on i) a standard softmax classifier ranging over all predicates as output, ii) a model that predicts a low-dimensional encoding of the property given entity representation and question, iii) a model that learns to score a pair of subject and predicate given the question as well as iv) a model based on the well-known FastText model. The comparison of architectures shows that FastText provides better results than other architectures. Copyright © 2018, The Authors. All rights reserved.

关键词： Architectural design

来源：评论

学校读者我要写书评

暂无评论

Evaluating Question Answering over Linked Data

SSRN

引用

SSRN 2018年

作者： Lopez, Vanessa Unger, Christina Cimiano, Philipp Motta, Enrico IBM Research Smarter Cities Technology Centre Mulhuddart Dublin Ireland Semantic Computing Group CITEC Universität Bielefeld Bielefeld Germany Knowledge Media Institute The Open University Milton Keynes United Kingdom

The availability of large amounts of open, distributed and structured semantic data on the web has no precedent in the history of computer science. In recent years, there have been important advances in semantic search and question answering over RDF data. In particular, natural language interfaces to online semantic data have the advantage that they can exploit the expressive power of semantic Web data models and query languages, while at the same time hiding their complexity from the user. However, despite the increasing interest in this area, there are no evaluations so far that systematically evaluate this kind of systems, in contrast to traditional question answering and search interfaces to document spaces. To address this gap, we have set up a series of evaluation challenges for question answering over linked data. The main goal of the challenge was to get insight into the strengths, capabilities and current shortcomings of question answering systems as interfaces to query linked data sources, as well as benchmarking how these interaction paradigms can deal with the fact that the amount of RDF data available on the web is very large and heterogeneous with respect to the vocabularies and schemas used. Here we report on the results from the first and second of such evaluation campaigns. We also discuss how the second evaluation addressed some of the issues and limitations which arose from the first one, as well as the open issues to be addressed in future competitions. © 2018, The Authors. All rights reserved.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Comparing hidden Markov models and long short term memory neural networks for learning action representations 1

引用

2nd International Workshop on Machine Learning, Optimization and Big Data, MOD 2016

作者： Panzner, Maximilian Cimiano, Philipp Semantic Computing Group CITEC Bielefeld University Bielefeld Germany

ISBN: (数字)9783319514697

ISBN: (纸本)9783319514680

In this paper we are concerned with learning models of actions and compare a purely generative model based on Hidden Markov Models to a discriminatively trained recurrent LSTM network in terms of their properties and their suitability to learn and represent models of actions. Specifically we compare the performance of the two models regarding the overall classification accuracy, the amount of training sequences required and how early in the progression of a sequence they are able to correctly classify the corresponding sequence. We show that, despite the current trend towards (deep) neural networks, traditional graphical model approaches are still beneficial under conditions where only few data points or limited computing power is available. © Springer International Publishing AG 2016.

关键词： Hidden Markov models

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：