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

by   Sherzod Hakimov, et al.

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.


Deep Learning Approaches for Question Answering on Knowledge Bases: an evaluation of architectural design choices

The task of answering natural language questions over knowledge bases ha...

Knowledge Base Completion using Web-Based Question Answering and Multimodal Fusion

Over the past few years, large knowledge bases have been constructed to ...

Unsupervised Deep Learning based Multiple Choices Question Answering: Start Learning from Basic Knowledge

In this paper, we study the possibility of almost unsupervised Multiple ...

Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases

When answering natural language questions over knowledge bases (KB), dif...

Simple Question Answering by Attentive Convolutional Neural Network

This work focuses on answering single-relation factoid questions over Fr...

Question Embeddings Based on Shannon Entropy: Solving intent classification task in goal-oriented dialogue system

Question-answering systems and voice assistants are becoming major part ...

Please sign up or login with your details

Forgot password? Click here to reset