Large pretrained models have seen enormous success in extractive summarization tasks.
We introduce HoVer (HOppy VERification), a dataset for many-hop evidence extraction and fact verification.
We investigate the extent to which individual attention heads in pretrained transformer language models, such as BERT and RoBERTa, implicitly capture syntactic dependency relations.
1 code implementation • • 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 Jeretič, Samuel R. Bowman
We conclude that a variety of methods is necessary to reveal all relevant aspects of a model's grammatical knowledge in a given domain.
The Word Embedding Association Test shows that GloVe and word2vec word embeddings exhibit human-like implicit biases based on gender, race, and other social constructs (Caliskan et al., 2017).