Offspring from Reproduction Problems: What Replication Failure Teaches Us
By Antske Fokkens, Marieke van Erp, Marten Postma, Ted Pedersen, Piek T. J. M. Vossen, Nuno Freire. 2013
120 citations recorded by the source corpus.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Margaret E. Roberts
- Iryna Gurevych
- Federico Bianchi
- Brandon M Stewart
- Dirk Hovy
- Dustin Tingley
- Nils Reimers
- Christopher Lucas
Citations in the corpus
- Reporting Score Distributions Makes a Difference: Performance Study of LSTM-networks for Sequence Tagging (2017, background): “Fokkens et al. (2013) show that reproducing results is not always straight-forward, as factors like preprocessing (e.g. tok-enization), experimental setup (e.g. splitting data), the version of components, the exact implementation of features, and the treatment of ties can have a major impact on the…”
- We Need to Talk about Standard Splits (2019, background): “Researchers attempting replications or reproductions have reported problems with availability of data (Mieskes, 2017; Wieling et al., 2018) and software (Pedersen, 2008), and various details of implementation (Fokkens et al., 2013; Reimers and Gurevych, 2017; Schluter and Varab, 2018).”
- Computer-Assisted Text Analysis for Comparative Politics (2015, background): “Fokkens et al. (2013) found that differing removal of stop words can produce different results in some cases.”
- On the Gap between Adoption and Understanding in NLP (2021, background): “Fokkens et al. (2013) already identified five parameters for better reproducibility.”
- State of the Art: Reproducibility in Artificial Intelligence (2018, background): “Despite of this, the percentage of research that is reproducible is not higher for machine learning and artificial intelligence (AI) research (Hunold and Träff 2013; Fokkens et al. 2013; Hunold 2015).”
- Text Preprocessing for Text Mining in Organizational Research: Review and Recommendations (2020, background): “Despite its importance, text preprocessing is often glossed over and poorly reported in text mining research (Fokkens et al., 2013).”