H
Hagen Blix
Researcher at New York University
Publications - 10
Citations - 155
Hagen Blix is an academic researcher from New York University. The author has contributed to research in topics: Noun & Declension. The author has an hindex of 4, co-authored 8 publications receiving 85 citations.
Papers
More filters
Proceedings ArticleDOI
Investigating Bert's knowledge of language: Five analysis methods with NPIs
Alex Warstadt,Yu Cao,Ioana Grosu,Wei Peng,Hagen Blix,Yining Nie,Anna Alsop,Shikha Bordia,Haokun Liu,Alicia Parrish,Sheng-Fu Wang,Jason Phang,Anhad Mohananey,Phu Mon Htut,Paloma Jeretic,Samuel R. Bowman +15 more
TL;DR: The authors explore five experimental methods inspired by prior work evaluating pretrained sentence representation models, and find that BERT has significant knowledge of these features, but its success varies widely across different experimental methods.
Posted Content
Investigating BERT's Knowledge of Language: Five Analysis Methods with NPIs
Alex Warstadt,Yu Cao,Ioana Grosu,Wei Peng,Hagen Blix,Yining Nie,Anna Alsop,Shikha Bordia,Haokun Liu,Alicia Parrish,Sheng-Fu Wang,Jason Phang,Anhad Mohananey,Phu Mon Htut,Paloma Jeretic,Samuel R. Bowman +15 more
TL;DR: It is concluded that a variety of methods is necessary to reveal all relevant aspects of a model’s grammatical knowledge in a given domain.
Proceedings ArticleDOI
On the Machine Learning of Ethical Judgments from Natural Language
TL;DR: Through an audit of recent work on computational approaches for predicting morality, this work examines the broader issues that arise from such efforts and offers a critique of such NLP methods for automating ethical decision-making.
Proceedings ArticleDOI
Predicting Declension Class from Form and Meaning
TL;DR: This article investigated the strength of those clues and found that the form and meaning of nouns can provide imperfect clues for declension class classification in many Indo-European languages (Czech and German) and showed that the three-way interaction between class, form, and meaning is significant.
Posted Content
Predicting Declension Class from Form and Meaning
TL;DR: This study introduces a new method that provides additional quantitative support for a classic linguistic finding that form and meaning are relevant for the classification of nouns into declensions and shows not only that individual declensions classes vary in the strength of their clues within a language, but also that these variations themselves vary across languages.