The Web as a Knowledge-base for Answering Complex Questions

TL;DR

This paper introduces a novel framework that decomposes complex questions into simpler ones, leveraging web search and reading comprehension to improve answer accuracy, demonstrated on a new dataset with significant performance gains.

Contribution

It presents a new question decomposition approach combined with web interaction for answering complex questions, along with a new dataset, ComplexWebQuestions.

Findings

Question decomposition improves precision@1 from 20.8 to 27.5.

The framework effectively handles broad and complex questions.

A new dataset for complex question answering is introduced.

Abstract

Answering complex questions is a time-consuming activity for humans that requires reasoning and integration of information. Recent work on reading comprehension made headway in answering simple questions, but tackling complex questions is still an ongoing research challenge. Conversely, semantic parsers have been successful at handling compositionality, but only when the information resides in a target knowledge-base. In this paper, we present a novel framework for answering broad and complex questions, assuming answering simple questions is possible using a search engine and a reading comprehension model. We propose to decompose complex questions into a sequence of simple questions, and compute the final answer from the sequence of answers. To illustrate the viability of our approach, we create a new dataset of complex questions, ComplexWebQuestions, and present a model that decomposes questions and interacts with the web to compute an answer. We empirically demonstrate that question decomposition improves performance from 20.8 precision@1 to 27.5 precision@1 on this new dataset.