1 code implementation • CRAC (ACL) 2021 • Andreas van Cranenburgh, Esther Ploeger, Frank van den Berg, Remi Thüss
We introduce a modular, hybrid coreference resolution system that extends a rule-based baseline with three neural classifiers for the subtasks mention detection, mention attributes (gender, animacy, number), and pronoun resolution.
1 code implementation • EMNLP (LaTeCHCLfL, CLFL, LaTeCH) 2021 • Andreas van Cranenburgh, Erik Ketzan
This paper applies stylometry to quantify the literariness of 73 novels and novellas by American author Stephen King, chosen as an extraordinary case of a writer who has been dubbed both “high” and “low” in literariness in critical reception.
1 code implementation • COLING (LaTeCHCLfL, CLFL, LaTeCH) 2020 • Andreas van Cranenburgh, Corina Koolen
In an exploratory analysis, we compare the ratings to those from the large reader survey of the Riddle in which social factors were not excluded, and to machine learning predictions of those literary ratings.
1 code implementation • COLING (CRAC) 2020 • Corbèn Poot, Andreas van Cranenburgh
We evaluate a rule-based (Lee et al., 2013) and neural (Lee et al., 2018) coreference system on Dutch datasets of two domains: literary novels and news/Wikipedia text.
1 code implementation • ACL 2020 • Stéphan Tulkens, Andreas van Cranenburgh
We present a simple but effective method for aspect identification in sentiment analysis.
Ranked #1 on Aspect Category Detection on Citysearch
2 code implementations • Findings of the Association for Computational Linguistics 2020 • Wietse de Vries, Andreas van Cranenburgh, Malvina Nissim
Peeking into the inner workings of BERT has shown that its layers resemble the classical NLP pipeline, with progressively more complex tasks being concentrated in later layers.
2 code implementations • 19 Dec 2019 • Wietse de Vries, Andreas van Cranenburgh, Arianna Bisazza, Tommaso Caselli, Gertjan van Noord, Malvina Nissim
The transformer-based pre-trained language model BERT has helped to improve state-of-the-art performance on many natural language processing (NLP) tasks.
Ranked #3 on Sentiment Analysis on DBRD
1 code implementation • Language Resources and Evaluation 2019 • Andreas van Cranenburgh, Karina van Dalen-Oskam, Joris van Zundert
Previous research showed that ratings of literariness are predictable from texts to a substantial extent using machine learning, suggesting that it may be possible to explain the consensus among readers on which novels are literary as a consensus on the kind of writing style that characterizes literature.
1 code implementation • COLING 2018 • Andreas van Cranenburgh
We present a language-independent treebank annotation tool supporting rich annotations with discontinuous constituents and function tags.
1 code implementation • COLING 2018 • Andreas van Cranenburgh
Should writers {``}avoid clich{\'e}s like the plague{''}?
no code implementations • ACL 2018 • Tatiana Bladier, Andreas van Cranenburgh, Younes Samih, Laura Kallmeyer
We present ongoing work on data-driven parsing of German and French with Lexicalized Tree Adjoining Grammars.
no code implementations • WS 2017 • Corina Koolen, Andreas van Cranenburgh
Stylometric and text categorization results show that author gender can be discerned in texts with relatively high accuracy.
1 code implementation • EACL 2017 • Andreas van Cranenburgh, Rens Bod
We consider the task of predicting how literary a text is, with a gold standard from human ratings.
1 code implementation • 1 Oct 2014 • Dirk Roorda, Gino Kalkman, Martijn Naaijer, Andreas van Cranenburgh
The Linguistic Annotation Framework (LAF) provides a general, extensible stand-off markup system for corpora.
no code implementations • LREC 2012 • Maria Aloni, Andreas van Cranenburgh, Raquel Fern{\'a}ndez, Marta Sznajder
Natural languages possess a wealth of indefinite forms that typically differ in distribution and interpretation.