Papers by Nasrin Mostafazadeh

2 papers
GLUCOSE: GeneraLized and COntextualized Story Explanations (2020.emnlp-main)

Copied to clipboard

Challenge: Existing knowledge resources and pretrained language models do not include or readily predict GLUCOSE’s rich inferential content.
Approach: They propose a platform for crowdsourcing GLUCOSE data at scale that uses semi-structured templates to elicit causal explanations.
Outcome: The proposed model can be trained on human-readable stories and build similar models on unseen stories.
Tackling the Story Ending Biases in The Story Cloze Test (P18-2)

Copied to clipboard

Challenge: Story Cloze Test (SCT) is a recent framework for evaluating story comprehension and script learning.
Approach: They propose to use a crowdsourcing scheme to create a new SCT dataset to overcome some of the biases discovered in the original SCT.
Outcome: The proposed model performs better than the baselines on the SCT dataset, despite human-authorship biases.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations