Stochastic Answer Networks for SQuAD 2.0

September 24, 2018 · Entered Twilight · 🏛 arXiv.org

"Last commit was 7.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, LICENSE.txt, README.md, config.py, download.sh, launch_docker.sh, my_utils, prepro.py, requirements.txt, resource, run.sh, san_log.txt, src, train.py

Authors Xiaodong Liu, Wei Li, Yuwei Fang, Aerin Kim, Kevin Duh, Jianfeng Gao arXiv ID 1809.09194 Category cs.CL: Computation & Language Citations 24 Venue arXiv.org Repository https://github.com/kevinduh/san_mrc ⭐ 149 Last Checked 1 month ago

Abstract

This paper presents an extension of the Stochastic Answer Network (SAN), one of the state-of-the-art machine reading comprehension models, to be able to judge whether a question is unanswerable or not. The extended SAN contains two components: a span detector and a binary classifier for judging whether the question is unanswerable, and both components are jointly optimized. Experiments show that SAN achieves the results competitive to the state-of-the-art on Stanford Question Answering Dataset (SQuAD) 2.0. To facilitate the research on this field, we release our code: https://github.com/kevinduh/san_mrc.