129 citations · 129 across the 2 of their papers we have counts for
4 papers
Fine-Grained Entity Typing in Hyperbolic Space
Federico López, Benjamin Heinzerling, Michael Strube
How can we represent hierarchical information present in large type inventories for entity typing? We study the ability of hyperbolic embeddings to capture hierarchical relations b…
Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation
Benjamin Heinzerling, Michael Strube
Pretrained contextual and non-contextual subword embeddings have become available in over 250 languages, allowing massively multilingual NLP. However, while there is no dearth of p…
BPEmb: Tokenization-free Pre-trained Subword Embeddings in 275 Languages
Benjamin Heinzerling, Michael Strube
We present BPEmb, a collection of pre-trained subword unit embeddings in 275 languages, based on Byte-Pair Encoding (BPE). In an evaluation using fine-grained entity typing as test…
Revisiting Selectional Preferences for Coreference Resolution
Benjamin Heinzerling, Nafise Sadat Moosavi, Michael Strube
Selectional preferences have long been claimed to be essential for coreference resolution. However, they are mainly modeled only implicitly by current coreference resolvers. We pro…