# Evaluating Architectural Choices for Deep Learning Approaches for Question Answering over Knowledge Bases

## TL;DR

This paper systematically compares four deep learning architectures for question answering over knowledge bases, revealing that FastText-based models outperform others in accuracy under the same conditions.

## Contribution

It provides a fair evaluation of different deep learning architectures for KB question answering, highlighting the effectiveness of FastText models.

## Key findings

- FastText outperforms other architectures in predicate inference.
- Systematic comparison under identical conditions clarifies architecture impacts.
- Evaluation on simple questions with subject and predicate prediction.

## Abstract

The task of answering natural language questions over knowledge bases has received wide attention in recent years. Various deep learning architectures have been proposed for this task. However, architectural design choices are typically not systematically compared nor evaluated under the same conditions. In this paper, we contribute to a better understanding of the impact of architectural design choices by evaluating four different architectures under the same conditions. We address the task of answering simple questions, consisting in predicting the subject and predicate of a triple given a question. In order to provide a fair comparison of different architectures, we evaluate them under the same strategy for inferring the subject, and compare different architectures for inferring the predicate. The architecture for inferring the subject is based on a standard LSTM model trained to recognize the span of the subject in the question and on a linking component that links the subject span to an entity in the knowledge base. The architectures for predicate inference are based on i) a standard softmax classifier ranging over all predicates as output, iii) a model that predicts a low-dimensional encoding of the property given entity representation and question, iii) a model that learns to score a pair of subject and predicate given the question as well as iv) a model based on the well-known FastText model. The comparison of architectures shows that FastText provides better results than other architectures.