D
Douwe Kiela
Researcher at Facebook
Publications - 153
Citations - 11846
Douwe Kiela is an academic researcher from Facebook. The author has contributed to research in topics: Natural language & Computer science. The author has an hindex of 45, co-authored 152 publications receiving 8464 citations. Previous affiliations of Douwe Kiela include University of Cambridge & Katholieke Universiteit Leuven.
Papers
More filters
Proceedings ArticleDOI
Multi-Dimensional Gender Bias Classification
TL;DR: The authors proposed a fine-grained framework that decomposes gender bias in text along several pragmatic and semantic dimensions: bias from the gender of the person being spoken about, bias from gender of a person speaking to the speaker, and bias from a speaker's gender.
Posted Content
Virtual Embodiment: A Scalable Long-Term Strategy for Artificial Intelligence Research
TL;DR: Virtual embodiment is proposed as an alternative, long-term strategy for AI research that is multi-modal in nature and that allows for the kind of scalability required to develop the field coherently and incrementally, in an ethically responsible fashion.
Posted Content
ANLIzing the Adversarial Natural Language Inference Dataset.
TL;DR: An in-depth error analysis of Adversarial NLI (ANLI), a recently introduced large-scale human-and-model-in-the-loop natural language inference dataset collected over multiple rounds, and a fine-grained annotation scheme of the different aspects of inference that are responsible for the gold classification labels is proposed.
Proceedings ArticleDOI
Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings
TL;DR: A new method combining hyperbolic embeddings and Hearst patterns is proposed to set appropriate constraints for inferring concept hierarchies from distributional contexts while also being able to predict missing “is-a”-relationships and to correct wrong extractions.
Posted Content
Grasping the Finer Point: A Supervised Similarity Network for Metaphor Detection
TL;DR: The authors presented the first deep learning architecture designed to capture metaphorical composition and showed that it outperforms the existing approaches in the metaphor identification task, which is an important problem for natural language understanding.