Work

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

Year: 2018

Type: conference-paper

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 entitylinked 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: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/d18-1455

Authors: Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, William Cohen

Institution: Carnegie Mellon University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Science Foundation, Nvidia, Office of Naval Research

Awards: G3550935145, BIGDATA: Small: Big Data for Everyone, SHF: Large: Collaborative Research: Exploiting the Naturalness of Software