Open-Vocabulary Semantic Parsing with both Distributional Statistics and Formal Knowledge

TL;DR

This paper introduces a novel semantic parser that combines formal knowledge bases and distributional statistics from text corpora, enabling open-vocabulary, schema-independent question answering with improved accuracy.

Contribution

It presents the first model to integrate formal KBs and distributional data for semantic parsing, enhancing open-vocabulary question answering capabilities.

Findings

Significantly outperforms state-of-the-art baselines

Successfully leverages both KB and corpus information

Produces compositional, executable language representations

Abstract

Traditional semantic parsers map language onto compositional, executable queries in a fixed schema. This mapping allows them to effectively leverage the information contained in large, formal knowledge bases (KBs, e.g., Freebase) to answer questions, but it is also fundamentally limiting---these semantic parsers can only assign meaning to language that falls within the KB's manually-produced schema. Recently proposed methods for open vocabulary semantic parsing overcome this limitation by learning execution models for arbitrary language, essentially using a text corpus as a kind of knowledge base. However, all prior approaches to open vocabulary semantic parsing replace a formal KB with textual information, making no use of the KB in their models. We show how to combine the disparate representations used by these two approaches, presenting for the first time a semantic parser that (1) produces compositional, executable representations of language, (2) can successfully leverage the information contained in both a formal KB and a large corpus, and (3) is not limited to the schema of the underlying KB. We demonstrate significantly improved performance over state-of-the-art baselines on an open-domain natural language question answering task.