Open Question Answering with Weakly Supervised Embedding Models

TL;DR

This paper introduces a novel weakly supervised embedding approach for open question answering that learns to map questions and answers into a shared vector space, enabling schema-independent querying without extensive labeled data.

Contribution

It proposes a new training method combining stochastic gradient descent and fine-tuning with weak supervision, significantly improving over previous weakly labeled data methods.

Findings

Model captures meaningful signals from noisy supervision

Achieves major improvements over Paralex

Enables schema-independent question answering

Abstract

Building computers able to answer questions on any subject is a long standing goal of artificial intelligence. Promising progress has recently been achieved by methods that learn to map questions to logical forms or database queries. Such approaches can be effective but at the cost of either large amounts of human-labeled data or by defining lexicons and grammars tailored by practitioners. In this paper, we instead take the radical approach of learning to map questions to vectorial feature representations. By mapping answers into the same space one can query any knowledge base independent of its schema, without requiring any grammar or lexicon. Our method is trained with a new optimization procedure combining stochastic gradient descent followed by a fine-tuning step using the weak supervision provided by blending automatically and collaboratively generated resources. We empirically demonstrate that our model can capture meaningful signals from its noisy supervision leading to major improvements over paralex, the only existing method able to be trained on similar weakly labeled data.