The Web as a Knowledge-base for Answering Complex Questions
This addresses the problem of time-consuming complex question answering for users by providing an incremental improvement over existing methods.
The paper tackles the challenge of answering complex questions by decomposing them into sequences of simple questions and using a search engine with a reading comprehension model to compute answers, achieving an improvement from 20.8 to 27.5 precision@1 on a new dataset.
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.