scispace - formally typeset
M

Michael Strube

Researcher at University of Pennsylvania

Publications -  169
Citations -  7315

Michael Strube is an academic researcher from University of Pennsylvania. The author has contributed to research in topics: Coreference & Sentence. The author has an hindex of 40, co-authored 155 publications receiving 6389 citations. Previous affiliations of Michael Strube include Heidelberg Institute for Theoretical Studies & University of Freiburg.

Papers
More filters
Proceedings Article

WikiRelate! computing semantic relatedness using wikipedia

TL;DR: This work presents experiments on using Wikipedia for computing semantic relatedness and compares it to WordNet on various benchmarking datasets, and shows that Wikipedia outperforms WordNet when applied to the largest available dataset designed for that purpose.
Proceedings Article

Deriving a large scale taxonomy from Wikipedia

TL;DR: A large scale taxonomy containing a large amount of subsumption is derived using methods based on connectivity in the network and lexicosyntactic matching to label the semantic relations between categories in Wikipedia.
Journal Article

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Aarohi Srivastava, +439 more
- 09 Jun 2022 - 
TL;DR: Evaluation of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters finds that model performance and calibration both improve with scale, but are poor in absolute terms.
Proceedings ArticleDOI

Exploiting Semantic Role Labeling, WordNet and Wikipedia for Coreference Resolution

TL;DR: An extension of a machine learning based coreference resolution system which uses features induced from different semantic knowledge sources, which represent knowledge mined from WordNet and Wikipedia, as well as information about semantic role labels is presented.
Journal ArticleDOI

Knowledge derived from wikipedia for computing semantic relatedness

TL;DR: Existing relatedness measures perform better using Wikipedia than a baseline given by Google counts, and it is shown that Wikipedia outperforms WordNet on some datasets.