1 code implementation • ACL 2022 • Lihu Chen, Gael Varoquaux, Fabian Suchanek
State-of-the-art NLP systems represent inputs with word embeddings, but these are brittle when faced with Out-of-Vocabulary (OOV) words. To address this issue, we follow the principle of mimick-like models to generate vectors for unseen words, by learning the behavior of pre-trained embeddings using only the surface form of words. We present a simple contrastive learning framework, LOVE, which extends the word representation of an existing pre-trained language model (such as BERT) and makes it robust to OOV with few additional parameters. Extensive evaluations demonstrate that our lightweight model achieves similar or even better performances than prior competitors, both on original datasets and on corrupted variants.
no code implementations • LREC 2022 • Yaru Wu, Fabian Suchanek, Ioana Vasilescu, Lori Lamel, Martine Adda-Decker
Speech characteristics vary from speaker to speaker.
1 code implementation • 16 Nov 2023 • Chadi Helwe, Tom Calamai, Pierre-Henri Paris, Chloé Clavel, Fabian Suchanek
We introduce MAFALDA, a benchmark for fallacy classification that merges and unites previous fallacy datasets.
1 code implementation • 23 Aug 2023 • Fabian Suchanek, Mehwish Alam, Thomas Bonald, Lihu Chen, Pierre-Henri Paris, Jules Soria
Knowledge Bases (KBs) find applications in many knowledge-intensive tasks and, most notably, in information retrieval.
no code implementations • 18 May 2023 • Nedeljko Radulovic, Albert Bifet, Fabian Suchanek
BELLA provides explanations in the form of a linear model trained in the feature space.
no code implementations • 9 May 2023 • Simon Razniewski, Hiba Arnaout, Shrestha Ghosh, Fabian Suchanek
General-purpose knowledge bases (KBs) are a cornerstone of knowledge-centric AI.
no code implementations • 24 Sep 2020 • Gerhard Weikum, Luna Dong, Simon Razniewski, Fabian Suchanek
Equipping machines with comprehensive knowledge of the world's entities and their relationships has been a long-standing goal of AI.
no code implementations • 21 Feb 2020 • Jérôme Dockès, Russell Poldrack, Romain Primet, Hande Gözükan, Tal Yarkoni, Fabian Suchanek, Bertrand Thirion, Gaël Varoquaux
Reaching a global view of brain organization requires assembling evidence on widely different mental processes and mechanisms.
no code implementations • 4 Jun 2018 • Jérôme Dockès, Demian Wassermann, Russell Poldrack, Fabian Suchanek, Bertrand Thirion, Gaël Varoquaux
In this paper, we propose to mine brain medical publications to learn the spatial distribution associated with anatomical terms.