1 code implementation • 1 May 2021 • Marshall Ho, Zhipeng Zhou, Judith He
We present 3 different question-answering models trained on the SQuAD2. 0 dataset -- BIDAF, DocumentQA and ALBERT Retro-Reader -- demonstrating the improvement of language models in the past three years.
1 code implementation • 7 Feb 2021 • Allen Bao, Marshall Ho, Saarthak Sangamnerkar
This paper presents an NLP (Natural Language Processing) approach to detecting spoilers in book reviews, using the University of California San Diego (UCSD) Goodreads Spoiler dataset.