1 code implementation • 17 Feb 2025 • Michiel van der Meer, Pavel Korshunov, Sébastien Marcel, Lonneke van der Plas
We find that well-configured lightweight text-based encoders perform comparably to multimodal models but the first only focus on identifying non-claim-like content.
1 code implementation • 4 Nov 2024 • Mete Ismayilzada, Claire Stevenson, Lonneke van der Plas
Storytelling is a fundamental aspect of human communication, relying heavily on creativity to produce narratives that are novel, appropriate, and surprising.
1 code implementation • 22 Oct 2024 • Mete Ismayilzada, Debjit Paul, Antoine Bosselut, Lonneke van der Plas
Creativity is the ability to produce novel, useful, and surprising ideas, and has been widely studied as a crucial aspect of human cognition.
no code implementations • 16 Oct 2024 • Mete Ismayilzada, Defne Circi, Jonne Sälevä, Hale Sirin, Abdullatif Köksal, Bhuwan Dhingra, Antoine Bosselut, Lonneke van der Plas, Duygu Ataman
While humans exhibit compositional generalization and linguistic creativity in language use, the extent to which LLMs replicate these abilities, particularly in morphology, is under-explored.
1 code implementation • 20 Feb 2024 • Vincent Jung, Lonneke van der Plas
We study the effect of one type of imbalance often present in real-life multilingual classification datasets: an uneven distribution of labels across languages.
1 code implementation • 9 Oct 2023 • Molly R. Petersen, Lonneke van der Plas
While analogies are a common way to evaluate word embeddings in NLP, it is also of interest to investigate whether or not analogical reasoning is a task in itself that can be learned.
1 code implementation • DeepLo 2022 • Kurt Micallef, Albert Gatt, Marc Tanti, Lonneke van der Plas, Claudia Borg
We also present a newly created corpus for Maltese, and determine the effect that the pre-training data size and domain have on the downstream performance.
no code implementations • 15 Nov 2021 • Andrea DeMarco, Carlos Mena, Albert Gatt, Claudia Borg, Aiden Williams, Lonneke van der Plas
Recent years have seen an increased interest in the computational speech processing of Maltese, but resources remain sparse.
1 code implementation • EMNLP (BlackboxNLP) 2021 • Marc Tanti, Lonneke van der Plas, Claudia Borg, Albert Gatt
Recent work has shown evidence that the knowledge acquired by multilingual BERT (mBERT) has two components: a language-specific and a language-neutral one.
no code implementations • LREC 2020 • Stavros Assimakopoulos, Rebecca Vella Muskat, Lonneke van der Plas, Albert Gatt
In view of this, we suggest a multi-layer annotation scheme, which is pilot-tested against a binary +/- hate speech classification and appears to yield higher inter-annotator agreement.
no code implementations • LREC 2020 • Carlos Mena, Albert Gatt, Andrea DeMarco, Claudia Borg, Lonneke van der Plas, Amanda Muscat, Ian Padovani
Maltese, the national language of Malta, is spoken by approximately 500, 000 people.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
no code implementations • 23 Jul 2020 • Michele Loi, Eleonora Viganò, Lonneke van der Plas
In this paper, we provide a philosophical account of the value of creative systems for individuals and society.
no code implementations • 21 Jun 2020 • Michele Loi, Lonneke van der Plas
With this paper, we aim to put an issue on the agenda of AI ethics that in our view is overlooked in the current discourse.
no code implementations • LREC 2020 • Colin Layfield, Lonneke van der Plas, Michael Rosner, John Abela
The Voynich Manuscript has baffled scholars for centuries.
1 code implementation • WS 2019 • Prajit Dhar, Lonneke van der Plas
We introduce temporally and contextually-aware models for the novel task of predicting unseen but plausible concepts, as conveyed by noun-noun compounds in a time-stamped corpus.
1 code implementation • WS 2019 • Prajit Dhar, Janis Pagel, Lonneke van der Plas
We present work in progress on the temporal progression of compositionality in noun-noun compounds.
1 code implementation • LREC 2018 • Albert Gatt, Marc Tanti, Adrian Muscat, Patrizia Paggio, Reuben A. Farrugia, Claudia Borg, Kenneth P. Camilleri, Mike Rosner, Lonneke van der Plas
To gain a better understanding of the variation we find in face description and the possible issues that this may raise, we also conducted an annotation study on a subset of the corpus.
no code implementations • CL 2017 • Mathieu Constant, G{\"u}l{\c{s}}en Eryi{\v{g}}it, Johanna Monti, Lonneke van der Plas, Carlos Ramisch, Michael Rosner, Amalia Todirascu
The structure of linguistic processing that depends on the clear distinction between words and phrases has to be re-thought to accommodate MWEs.
no code implementations • WS 2017 • Hoa Trong Vu, Thuong-Hai Pham, Xiaoyu Bai, Marc Tanti, Lonneke van der Plas, Albert Gatt
System using BiLSTM and max pooling.
no code implementations • ACL 2017 • Glorianna Jagfeld, Patrick Ziering, Lonneke van der Plas
Traditionally, compound splitters are evaluated intrinsically on gold-standard data or extrinsically on the task of statistical machine translation.
no code implementations • WS 2016 • Gianina Iord{\u{a}}chioaia, Lonneke van der Plas, Glorianna Jagfeld
We present an interdisciplinary study on the interaction between the interpretation of noun-noun deverbal compounds (DCs; e. g., task assignment) and the morphosyntactic properties of their deverbal heads in English.