Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text

September 04, 2018 · Entered Twilight · 🏛 Conference on Empirical Methods in Natural Language Processing

"Last commit was 6.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, LICENSE, README.md, config, data_loader.py, environment.yml, graftnet.py, main.py, preprocessing, script.py, util.py, wikimovie_preprocessing

Authors Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, William W. Cohen arXiv ID 1809.00782 Category cs.CL: Computation & Language Cross-listed cs.LG Citations 477 Venue Conference on Empirical Methods in Natural Language Processing Repository https://github.com/OceanskySun/GraftNet ⭐ 265 Last Checked 1 month ago

Abstract

Open Domain Question Answering (QA) is evolving from complex pipelined systems to end-to-end deep neural networks. Specialized neural models have been developed for extracting answers from either text alone or Knowledge Bases (KBs) alone. In this paper we look at a more practical setting, namely QA over the combination of a KB and entity-linked text, which is appropriate when an incomplete KB is available with a large text corpus. Building on recent advances in graph representation learning we propose a novel model, GRAFT-Net, for extracting answers from a question-specific subgraph containing text and KB entities and relations. We construct a suite of benchmark tasks for this problem, varying the difficulty of questions, the amount of training data, and KB completeness. We show that GRAFT-Net is competitive with the state-of-the-art when tested using either KBs or text alone, and vastly outperforms existing methods in the combined setting. Source code is available at https://github.com/OceanskySun/GraftNet .