检索结果-内蒙古大学图书馆

4th Workshop on Human Evaluation of NLP Systems, HumEval 2024

作者： Miletić, Aleksandra Miletić, Filip Department of Digital Humanities University of Helsinki Finland Institute for Natural Language Processing University of Stuttgart Germany

ISBN: (纸本)9782493814418

Bosnian, Croatian, Montenegrin and Serbian are the official standard linguistic varieties in Bosnia and Herzegovina, Croatia, Montenegro, and Serbia, respectively. When these four countries were part of the former Yugoslavia, the varieties were considered to share a single linguistic standard. After the individual countries were established, the national standards emerged. Today, a central question about these varieties remains the following: How different are they from each other? How hard is it to distinguish them? While this has been addressed in NLP as part of the task on Distinguishing Between Similar languages (DSL), little is known about human performance, making it difficult to contextualize system results. We tackle this question by reannotating the existing BCMS dataset for DSL with annotators from all target regions. We release a new gold standard, replacing the original single-annotator, single-label annotation by a multi-annotator, multi-label one, thus improving annotation reliability and explicitly coding the existence of ambiguous instances. We reassess a previously proposed DSL system on the new gold standard and establish the human upper bound on the task. Finally, we identify sources of annotation difficulties and provide linguistic insights into the BCMS dialect continuum, with multiple indicators highlighting an intermediate position of Bosnian and Montenegrin. © 2024 European language Resources Association (ELRA).

关键词： digital subscriber lines

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Fallacy Detection with Human Label Variation

arXiv

引用

arXiv 2025年

作者： Ramponi, Alan Daffara, Agnese Tonelli, Sara Digital Humanities group Fondazione Bruno Kessler Italy Department of Humanities University of Pavia Italy Institute for Natural Language Processing University of Stuttgart Germany

We introduce FAINA, the first dataset for fallacy detection that embraces multiple plausible answers and natural disagreement. FAINA includes over 11K span-level annotations with overlaps across 20 fallacy types on social media posts in Italian about migration, climate change, and public health given by two expert annotators. Through an extensive annotation study that allowed discussion over multiple rounds, we minimize annotation errors whilst keeping signals of human label variation. Moreover, we devise a framework that goes beyond "single ground truth" evaluation and simultaneously accounts for multiple (equally reliable) test sets and the peculiarities of the task, i.e., partial span matches, overlaps, and the varying severity of labeling errors. Our experiments across four fallacy detection setups show that multi-task and multi-label transformer-based approaches are strong baselines across all settings. We release our data, code, and annotation guidelines to foster research on fallacy detection and human label variation more broadly.1 Copyright © 2025, The Authors. All rights reserved.

关键词： Electric transformer testing

来源：评论

学校读者我要写书评

暂无评论

DramaCoref: A Hybrid Coreference Resolution System for German Theater Plays 4

DramaCoref: A Hybrid Coreference Resolution System for Germa...

引用

4th Workshop on Computational Models of Reference, Anaphora and Coreference, CRAC 2021

作者： Pagel, Janis Reiter, Nils Institute for Natural Language Processing University of Stuttgart Germany Department of Digital Humanities University of Cologne Germany

ISBN: (纸本)9781955917025

We present a system for resolving coreference on theater plays, DramaCoref. The system uses neural network techniques to provide a list of potential mentions. These mentions are assigned to common entities using generic and domain-specific rules. We find that DramaCoref works well on the theater plays when compared to corpora from other domains and profits from the inclusion of information specific to theater plays. On the best-performing setup, it achieves a CoNLL score of 32% when using automatically detected mentions and 55% when using gold mentions. Single rules achieve high precision scores;however, rules designed on other domains are often not applicable or yield unsatisfactory results. Error analysis shows that the mention detection is the main weakness of the system, providing directions for future improvements. © 2021 Association for Computational Linguistics.

关键词： Theaters

来源：评论

学校读者我要写书评

暂无评论

Prosodic realisation of enjambment in recitations of German poetry 11

Prosodic realisation of enjambment in recitations of German ...

引用

11th International Conference on Speech Prosody, Speech Prosody 2022

作者： Schauffler, Nadja Schubö, Fabian Bernhart, Toni Eschenbach, Gunilla Koch, Julia Richter, Sandra Viehhauser, Gabriel Vu, Thang Wesemann, Lorenz Kuhn, Jonas Institute for Natural Language Processing University of Stuttgart Germany Institute of English Linguistics University of Stuttgart Germany Institute of Literary Studies/Digital Humanities University of Stuttgart Germany Marbach Germany

A salient feature of poetry is the organisation in lines and stanzas. Versification thus serves as a structural (and aesthetic) layer that either conforms to syntactic units or breaks them up. If line breaks disrupt syntactic units, we speak of enjambment - the line suggests a pause while the syntactic information continues. Since prosodic boundaries typically reflect syntactic boundaries, the question is which information is marked - the line or the syntactic unit. In a preliminary study with one professional speaker of German, we investigate how line breaks are prosodically realised in recitations of twenty poems by Friedrich Hölderlin. We compare cases of enjambment to line breaks without enjambment and look at lengthening of the line-final segment, frequency and duration of pauses and F0 reset across the line break, which are typical cues used for the prosodic marking of phrase boundaries in speech. We found that while pauses and F0 reset are tuned down in cases of enjambment, the line break is still prosodically marked by means of final lengthening. This preliminary result supports the idea that a speaker can convey both the syntactic continuity as well as the versification of the poem by strengthening different cues. © 2022 International Speech Communications Association. All rights reserved.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Using an explicit query and a topic model for scientific article recommendation

引用

Education and Information Technologies 2023年第12期28卷 15657-15670页

作者： Smail, Boussaadi Aliane, Hassina Abdeldjalil, Ouahabi DTISI Research Center on Scientific and Technical Information Cerist Algiers Algeria Director of Information Sciences R&D Laboratory Head of Natural Language Processing and Digital Content Team Cerist Algiers Algeria 1.Polytech Tours Imaging anBrain University of Tours INSERM U930 Tours France

The search for relevant scientific articles is a crucial step in any research project. However, the vast number of articles published and available online in digital databases (Google Scholar, Semantic Scholar, etc.) can make this task tedious and negatively impact a researcher's productivity. This article proposes a new method of recommending scientific articles that takes advantage of content-based filtering. The challenge is to target relevant information that meets a researcher's needs, regardless of their research domain. Our recommendation method is based on semantic exploration using latent factors. Our goal is to achieve an optimal topic model that will serve as the basis for the recommendation process. Our experiences confirm our performance expectations, showing relevance and objectivity in the results. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

关键词： Latent Dirichlet Allocation Non-negative Matrix Factorization Scientific article Scientific recommendation Topic modeling

来源：评论

学校读者我要写书评

暂无评论

Stateless and Rule-Based Verification For Compliance Checking Applications

arXiv

引用

arXiv 2022年

作者： Besharati, Mohammad Reza Izadi, Mohammad Asgari, Ehsaneddin Computer Engineering Department Sharif University of Technology Tehran Iran Natural Language Processing and Digital Humanities Laboratory Computer Engineering Department - AI Group Sharif University of Technology Tehran Iran

Underlying computational model has an important role in any computation. The state and transition (such as in automata) and rule and value (such asin Lisp andlogic programming) are two comparable andcounterpart computational models. Both ofdeductive andmodel checkingverificationtechniquesare relyingona notion of state andasa result, their underlyingcomputationalmodelsare state dependent. Some verificationproblems(such ascompliance checkingby which an undercompliance systemisverifiedagainst someregulationsand rules) have not a strongnotionof state nortransition. Behalf of it, these systemshave a strongnotionof value symbolsanddeclarative rules definedon them. SARV(StatelessAndRule-Based Verification) isa verificationframeworkthat designedto simplify the overall processof verificationfor statelessandrule-basedverificationproblems(e.g. compliancechecking). In this paper, a formal logic-based framework for creatingintelligent compliancecheckingsystemsispresented. We define andintroduce thisframework,report a case study andpresent resultsof an experiment onit. The case study isabout protocol compliance checkingfor smart cities. Usingthissolution,a Rescue Scenario use case and itscompliance checkingare sketchedandmodeled. An automationengine for anda compliance solution with SARV are introduced. Basedon 300data experiments,the SARV-basedcompliance solutionoutperformsfamousmachine learning methods on a 3125-records software quality dataset. © 2022, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Real-Valued Logics for Typological Universals: Framework and Application 28

Real-Valued Logics for Typological Universals: Framework and...

引用

28th International Conference on Computational Linguistics, COLING 2020

作者： Dönicke, Tillmann Yu, Xiang Kuhn, Jonas Göttingen Centre for Digital Humanities University of Göttingen Germany Institute for Natural Language Processing University of Stuttgart Germany

ISBN: (纸本)9781952148279

This paper proposes a framework for the expression of typological statements which uses real-valued logics to capture the empirical truth value (truth degree) of a formula on a given data source, e.g. a collection of multilingual treebanks with comparable annotation. The formulae can be arbitrarily complex expressions of propositional logic. To illustrate the usefulness of such a framework, we present experiments on the Universal Dependencies treebanks for two use cases: (i) empirical (re-)evaluation of established formulae against the spectrum of available treebanks and (ii) evaluating new formulae (i.e. potential candidates for universals) generated by a search algorithm. © 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.

关键词： Many valued logics

来源：评论

学校读者我要写书评

暂无评论

Predicting structural elements in German drama

Predicting structural elements in German drama

引用

2021 Conference on Computational humanities Research, CHR 2021

作者： Pagel, Janis Sihag, Nidhi Reiter, Nils Institute for Natural Language Processing University of Stuttgart Pfaffenwaldring 5b Stuttgart70569 Germany University of Stuttgart Keplerstrasse 7 Stuttgart70174 Germany Department of Digital Humanities University of Cologne Albertus-Magnus-Platz Cologne50931 Germany

We address the challenge of enriching plain text dramas with predicted TEI/XML elements. We use a large corpus of dramas annotated with TEI information about act/scene changes, speaker changes, and stage directions, among others. On this data, we fine-tune a pre-trained BERT transformer model on several subtasks, like predicting stage directions vs. utterances. We show that the used architecture is able to predict the learned structural elements on unseen data for several settings and models. © 2021 Copyright for this paper by its authors.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Recommender systems based on detection community in academic social network

Recommender systems based on detection community in academic...

引用

2020 International Multi-Conference on: Organization of Knowledge and Advanced Technologies", OCTA 2020

作者： Boussaadi, Smail Aliane, Hassina Abdeldjalil, Ouahabi Houari, Dihia Djoumagh, Malika Laboratory LIMPAF University of Bouira Algeria Information Sciences RD Laboratory Natural Language Processing and Digital Content Team. Cerist Algeria University of Bouira LIMPAF Computer Science Department Bouira Algeria

ISBN: (纸本)9781728164038

The speed with which new scientific articles are published and shared on academic social networks generated a situation of cognitive overload and the targeted access to the relevant information represents a major challenge for researchers. In this context, we propose a scientific article recommendation approach based on the discovery of thematic community structures, it focuses on the topological structure of the network combined with the analysis of the content of the social object (scientific article), a strategy that aims to mitigate the cold start problems and sparcity data in scoring matrix. A key element of our approach is the modeling of the researcher's thematic centers of interest derived from his corpus (a set of articles that interested him). In this perspective we use the technique of semantic exploration and extraction of latent topics in document corpora, LDA(Latent DirichletAllocation), an unsupervised learning method which offers the best solution of scalability problemcompared to other techniques of topic modeling. this technique allows us to build a profile model in the form of vectors in which the components are the probabilistic distributions on topics that reflect the interests of the researcher. The profile models thus constructed will be grouped into thematic clusters based on dominant topics using the fuzzy clustering algorithm, since the same topic can be treated in different scientific fields. Will follow a step of detection of community structures in thematic clusters to identify significant communities, the aim of this step is to project the recommendation process in a small space allowing better performance by reducing the computation time and the storage space for researcher/article data. The preliminary results of the experience of our approach on a population of 13 researchers and 60 articles shows that the articles generated by the recommendation process are very relevant to the target researcher or his community. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

The researchers profile with topic modeling 2

The researchers profile with topic modeling

引用

2nd IEEE International Conference on Electronics, Control, Optimization and Computer Science, ICECOCS 2020

作者： Boussaadi, Smail Aliane, Dr Hassina Abdeldjalil, Pr Ouahabi Laboratory LIMPAF University of Bouira Algeria Sciences RD Laboratory Head of Natural Language Processing and Digital Content Team Cerist Algiers Algeria Polytech Tours Imaging and Brain INSERM U930 University of Tours Tours France

ISBN: (纸本)9781728169217

Modeling the interests of researchers in academic social networks is a crucial step in a process of recommending scientific articles, linked to their areas of competence and expertise. In this context, a researcher profile constructed from non-observable variables on the basis of articles which interests him by the LDA (Latent Dirichlet Allocation) topic modeling technique allows the system to capture knowledge about his area of competence and skills, in order to predict these needs in terms of relevant research articles. In this article we are interested in the results produced by two different implementations of LDA Gensim and Mallet on the basis of information provided by the researchers (explicit information), in order to compare their interpretability and checked if they are reliable sources for model the areas of competence and expertise of scientists. © 2020 IEEE.

关键词： Statistics

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：