Publications

2020

  • A. Meroño-Peñuela, V. de Boer, M. van Erp, W. Melder, R. Mourits, A. Rijpma, R. Schalk, and R. Zijdeman, “Ontologies in clariah: towards interoperability in history, language and media,” in Arxiv preprint arxiv:2004.02845, , 2020.
    [Bibtex]
    @inbook{merono2020ontologies,
    title={Ontologies in CLARIAH: Towards Interoperability in History, Language and Media},
    author={Mero{\~n}o-Pe{\~n}uela, Albert and de Boer, Victor and van Erp, Marieke and Melder, Willem and Mourits, Rick and Rijpma, Auke and Schalk, Ruben and Zijdeman, Richard},
    booktitle={arXiv preprint arXiv:2004.02845},
    year={2020}
    }
  • T. Tietz, M. Alam, H. Sack, and M. van Erp, “Challenges of knowledge graph evolution from an nlp perspective,” in Proceedings of whise 2020, 2020.
    [Bibtex]
    @inproceedings{tietzchallenges,
    title={Challenges of Knowledge Graph Evolution from an NLP Perspective},
    author={Tietz, Tabea and Alam, Mehwish and Sack, Harald and van Erp, Marieke},
    booktitle={Proceedings of WHiSE 2020},
    year={2020}
    }
  • M. van Erp and P. Groth, “Towards entity spaces,” in Proceedings of the 12th language resources and evaluation conference, Marseille, France, 2020, p. 2129–2137.
    [Bibtex]
    @inproceedings{van-erp-groth-2020-towards,
    title = "Towards Entity Spaces",
    author = "van Erp, Marieke and
    Groth, Paul",
    booktitle = "Proceedings of The 12th Language Resources and Evaluation Conference",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://www.aclweb.org/anthology/2020.lrec-1.261",
    pages = "2129--2137",
    abstract = "Entities are a central element of knowledge bases and are important input to many knowledge-centric tasks including text analysis. For example, they allow us to find documents relevant to a specific entity irrespective of the underlying syntactic expression within a document. However, the entities that are commonly represented in knowledge bases are often a simplification of what is truly being referred to in text. For example, in a knowledge base, we may have an entity for Germany as a country but not for the more fuzzy concept of Germany that covers notions of German Population, German Drivers, and the German Government. Inspired by recent advances in contextual word embeddings, we introduce the concept of entity spaces - specific representations of a set of associated entities with near-identity. Thus, these entity spaces provide a handle to an amorphous grouping of entities. We developed a proof-of-concept for English showing how, through the introduction of entity spaces in the form of disambiguation pages, the recall of entity linking can be improved.",
    language = "English",
    ISBN = "979-10-95546-34-4",
    }
  • R. Ros, M. van Erp, A. Rijpma, and R. Zijdeman, “Mining wages in nineteenth-century job advertisements. the application of language resources and language technology to study economic and social inequality,” in Proceedings of the workshop about language resources for the ssh cloud, Marseille, France, 2020, p. 27–32.
    [Bibtex]
    @inproceedings{ros-etal-2020-mining,
    title = "Mining Wages in Nineteenth-Century Job Advertisements. The Application of Language Resources and Language Technology to study Economic and Social Inequality",
    author = "Ros, Ruben and
    van Erp, Marieke and
    Rijpma, Auke and
    Zijdeman, Richard",
    booktitle = "Proceedings of the Workshop about Language Resources for the SSH Cloud",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://www.aclweb.org/anthology/2020.lr4sshoc-1.5",
    pages = "27--32",
    abstract = "For the analysis of historical wage development, no structured data is available. Job advertisements, as found in newspapers can provide insights into what different types of jobs paid, but require language technology to structure in a format conducive to quantitative analysis. In this paper, we report on our experiments to mine wages from 19th century newspaper advertisements and detail the challenges that need to be overcome to perform a socio-economic analysis of textual data sources.",
    language = "English",
    ISBN = "979-10-95546-43-6",
    }
  • D. Deichmann, C. Moser, J. M. Birkholz, A. Nerghes, P. Groenewegen, and S. Wang, “Ideas with impact: how connectivity shapes idea diffusion,” Research policy, vol. 49, iss. 1, p. 103881, 2020.
    [Bibtex]
    @article{deichmann2020ideas,
    title={Ideas with impact: How connectivity shapes idea diffusion},
    author={Deichmann, Dirk and Moser, Christine and Birkholz, Julie M and Nerghes, Adina and Groenewegen, Peter and Wang, Shenghui},
    journal={Research policy},
    volume={49},
    number={1},
    pages={103881},
    year={2020},
    publisher={Elsevier}
    }
  • M. Wevers and M. Koolen, “Digital begriffsgeschichte: tracing semantic change using word embeddings,” Historical methods: a journal of quantitative and interdisciplinary history, p. 1–18, 2020.
    [Bibtex]
    @article{wevers2020digital,
    title={Digital begriffsgeschichte: Tracing semantic change using word embeddings},
    author={Wevers, Melvin and Koolen, Marijn},
    journal={Historical Methods: A Journal of Quantitative and Interdisciplinary History},
    pages={1--18},
    year={2020},
    publisher={Taylor \& Francis}
    }
  • M. Wevers and T. Smits, “The visual digital turn: using neural networks to study historical images,” Digital scholarship in the humanities, vol. 35, iss. 1, p. 194–207, 2020.
    [Bibtex]
    @article{wevers2020visual,
    title={The visual digital turn: Using neural networks to study historical images},
    author={Wevers, Melvin and Smits, Thomas},
    journal={Digital Scholarship in the Humanities},
    volume={35},
    number={1},
    pages={194--207},
    year={2020},
    publisher={Oxford University Press}
    }

2019

  • N. Dekker, T. Kuhn, and M. van Erp, “Evaluating named entity recognition tools for extracting social networks from novels,” Peerj computer science, vol. 5, p. e189, 2019.
    [Bibtex]
    @article{dekker2019evaluating,
    title={Evaluating named entity recognition tools for extracting social networks from novels},
    author={Dekker, Niels and Kuhn, Tobias and van Erp, Marieke},
    journal={PeerJ Computer Science},
    volume={5},
    pages={e189},
    year={2019},
    publisher={PeerJ Inc.}
    }
  • I. Keles, O. Qawasmeh, T. Tietz, L. Marinucci, R. Reda, and M. Van Erp, “A proposal for a two-way journey on validating locations in unstructured and structured data,” in 2nd conference on language, data and knowledge (ldk 2019), 2019.
    [Bibtex]
    @inproceedings{keles2019proposal,
    title={A Proposal for a Two-Way Journey on Validating Locations in Unstructured and Structured Data},
    author={Keles, Ilkcan and Qawasmeh, Omar and Tietz, Tabea and Marinucci, Ludovica and Reda, Roberto and Van Erp, Marieke},
    booktitle={2nd Conference on Language, Data and Knowledge (LDK 2019)},
    year={2019},
    organization={Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik}
    }
  • A. Nerghes and J. Lee, “Narratives of the refugee crisis: a comparative study of mainstream-media and twitter,” Media and communication, vol. 7, iss. 2 Refugee Crises Disclosed, p. 275–288, 2019.
    [Bibtex]
    @article{nerghes2019narratives,
    title={Narratives of the refugee crisis: A comparative study of mainstream-media and Twitter},
    author={Nerghes, Adina and Lee, Ju-Sung},
    journal={Media and Communication},
    volume={7},
    number={2 Refugee Crises Disclosed},
    pages={275--288},
    year={2019}
    }
  • [DOI] M. Wevers, “Using word embeddings to examine gender bias in Dutch newspapers, 1950-1990,” in Proceedings of the 1st international workshop on computational approaches to historical language change, Florence, Italy, 2019, p. 92–97.
    [Bibtex]
    @inproceedings{wevers-2019-using,
    title = "Using Word Embeddings to Examine Gender Bias in {D}utch Newspapers, 1950-1990",
    author = "Wevers, Melvin",
    booktitle = "Proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change",
    month = aug,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/W19-4712",
    doi = "10.18653/v1/W19-4712",
    pages = "92--97",
    abstract = "Contemporary debates on filter bubbles and polarization in public and social media raise the question to what extent news media of the past exhibited biases. This paper specifically examines bias related to gender in six Dutch national newspapers between 1950 and 1990. We measure bias related to gender by comparing local changes in word embedding models trained on newspapers with divergent ideological backgrounds. We demonstrate clear differences in gender bias and changes within and between newspapers over time. In relation to themes such as sexuality and leisure, we see the bias moving toward women, whereas, generally, the bias shifts in the direction of men, despite growing female employment number and feminist movements. Even though Dutch society became less stratified ideologically (depillarization), we found an increasing divergence in gender bias between religious and social-democratic on the one hand and liberal newspapers on the other. Methodologically, this paper illustrates how word embeddings can be used to examine historical language change. Future work will investigate how fine-tuning deep contextualized embedding models, such as ELMO, might be used for similar tasks with greater contextual information.",
    }
  • M. Wevers, J. Gao, and K. L. Nielbo, “Tracking the consumption junction: temporal dependencies between articles and advertisements in dutch newspapers,” Arxiv, vol. abs/1903.11461, 2019.
    [Bibtex]
    @article{Wevers2019TrackingTC,
    title={Tracking the Consumption Junction: Temporal Dependencies between Articles and Advertisements in Dutch Newspapers},
    author={Melvin Wevers and Jianbo Gao and Kristoffer L. Nielbo},
    journal={ArXiv},
    year={2019},
    volume={abs/1903.11461}
    }

2018

  • M. van Erp, M. Wevers, and H. Huurdeman, “Constructing a recipe web from historical newspapers,” in International semantic web conference, 2018, p. 217–232.
    [Bibtex]
    @inproceedings{van2018constructing,
    title={Constructing a recipe web from historical newspapers},
    author={van Erp, Marieke and Wevers, Melvin and Huurdeman, Hugo},
    booktitle={International Semantic Web Conference},
    pages={217--232},
    year={2018},
    organization={Springer}
    }
  • Proceedings of the workshop events and stories in the news 2018Santa Fe, New Mexico, U.S.A: Association for computational linguistics, 2018.
    [Bibtex]
    @proceedings{ws-2018-events,
    title = "Proceedings of the Workshop Events and Stories in the News 2018",
    editor = "Caselli, Tommaso and
    Miller, Ben and
    van Erp, Marieke and
    Vossen, Piek and
    Palmer, Martha and
    Hovy, Eduard and
    Mitamura, Teruko and
    Caswell, David and
    Brown, Susan W. and
    Bonial, Claire",
    month = aug,
    year = "2018",
    address = "Santa Fe, New Mexico, U.S.A",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/W18-4300",
    }
  • M. van Erp, J. de Does, K. Depuydt, R. Lenders, and T. van Goethem, “Slicing and dicing a newspaper corpus for historical ecology research,” in European knowledge acquisition workshop, 2018, p. 470–484.
    [Bibtex]
    @inproceedings{van2018slicing,
    title={Slicing and dicing a newspaper corpus for historical ecology research},
    author={van Erp, Marieke and de Does, Jesse and Depuydt, Katrien and Lenders, Rob and van Goethem, Thomas},
    booktitle={European Knowledge Acquisition Workshop},
    pages={470--484},
    year={2018},
    organization={Springer}
    }
  • J. Lee and A. Nerghes, “Refugee or migrant crisis? labels, perceived agency, and sentiment polarity in online discussions,” Social media+ society, vol. 4, iss. 3, p. 2056305118785638, 2018.
    [Bibtex]
    @article{lee2018refugee,
    title={Refugee or migrant crisis? Labels, perceived agency, and sentiment polarity in online discussions},
    author={Lee, Ju-Sung and Nerghes, Adina},
    journal={Social Media+ Society},
    volume={4},
    number={3},
    pages={2056305118785638},
    year={2018},
    publisher={SAGE Publications Sage UK: London, England}
    }
  • A. Nerghes and J. Lee, “The refugee/migrant crisis dichotomy on twitter: a network and sentiment perspective,” in Proceedings of the 10th acm conference on web science, 2018, p. 271–280.
    [Bibtex]
    @inproceedings{nerghes2018refugee,
    title={The refugee/migrant crisis dichotomy on Twitter: A network and sentiment perspective},
    author={Nerghes, Adina and Lee, Ju-Sung},
    booktitle={Proceedings of the 10th ACM conference on web science},
    pages={271--280},
    year={2018}
    }
  • A. Nerghes, P. Kerkhof, and I. Hellsten, “Early public responses to the zika-virus on youtube: prevalence of and differences between conspiracy theory and informational videos,” in Proceedings of the 10th acm conference on web science, 2018, p. 127–134.
    [Bibtex]
    @inproceedings{nerghes2018early,
    title={Early public responses to the Zika-virus on YouTube: Prevalence of and differences between conspiracy theory and informational videos},
    author={Nerghes, Adina and Kerkhof, Peter and Hellsten, Iina},
    booktitle={Proceedings of the 10th ACM Conference on Web Science},
    pages={127--134},
    year={2018}
    }
  • M. Wevers, “1928: coca-cola en de moderne consumptiemaatschappij,” in Wereldgeschiedenis van nederland, Amboanthos, 2018.
    [Bibtex]
    @inbook{wevers20181928,
    title={1928: Coca-Cola en de moderne consumptiemaatschappij},
    author={Wevers, Melvin},
    booktitle={Wereldgeschiedenis van Nederland},
    year={2018},
    publisher={AmboAnthos}
    }
  • M. Wevers and T. Smits, “Seeing history: analyzing large-scale historical visual datasets using deep neural networks,” , 2018.
    [Bibtex]
    @article{wevers2018seeing,
    title={Seeing History: Analyzing Large-scale Historical Visual Datasets Using Deep Neural Networks},
    author={Wevers, Melvin and Smits, Thomas},
    year={2018}
    }
  • M. Wevers, J. van Lottum, and M. van Erp, “Van kranten tot scheepspapieren en processtukken: rijkdom en verrijking van digitale bronnen voor onderzoek,” Archievenblad, vol. 122, iss. 3, p. 10–14, 2018.
    [Bibtex]
    @article{wevers2018van,
    title={Van kranten tot scheepspapieren en processtukken: Rijkdom en verrijking van digitale bronnen voor onderzoek},
    author={Wevers, Melvin and van Lottum, Jelle and van Erp, Marieke},
    journal={Archievenblad},
    volume={122},
    number={3},
    pages={10--14},
    year={2018}
    }

2017

  • M. Van Erp, T. van Goethem, K. Depuydt, and J. de Does, “Towards semantic enrichment of newspapers: a historical ecology use case.,” in Whise@ iswc, 2017, p. 39–44.
    [Bibtex]
    @inproceedings{van2017towards,
    title={Towards Semantic Enrichment of Newspapers: A Historical Ecology Use Case.},
    author={Van Erp, Marieke and van Goethem, Thomas and Depuydt, Katrien and de Does, Jesse},
    booktitle={WHiSe@ ISWC},
    pages={39--44},
    year={2017}
    }
  • L. Derczynski, E. Nichols, M. van Erp, and N. Limsopatham, “Results of the wnut2017 shared task on novel and emerging entity recognition,” in Proceedings of the 3rd workshop on noisy user-generated text, 2017, p. 140–147.
    [Bibtex]
    @inproceedings{derczynski2017results,
    title={Results of the WNUT2017 shared task on novel and emerging entity recognition},
    author={Derczynski, Leon and Nichols, Eric and van Erp, Marieke and Limsopatham, Nut},
    booktitle={Proceedings of the 3rd Workshop on Noisy User-generated Text},
    pages={140--147},
    year={2017}
    }