Relational Extraction on Wikipedia Tables using Convolutional and Memory Networks

TL;DR

This paper presents a neural network model combining CNN and BiLSTM for relation extraction from Wikipedia tables, outperforming previous methods and providing insights into model components and future research directions.

Contribution

Introduces a novel CNN-BiLSTM model specifically designed for relation extraction from tabular data, demonstrating improved performance over existing neural approaches.

Findings

Our model outperforms previous neural methods on a large dataset.

Comprehensive error and ablation analyses highlight the effectiveness of model components.

Discussion on the trade-offs and future research avenues for table-based relation extraction.

Abstract

Relation extraction (RE) is the task of extracting relations between entities in text. Most RE methods extract relations from free-form running text and leave out other rich data sources, such as tables. We explore RE from the perspective of applying neural methods on tabularly organized data. We introduce a new model consisting of Convolutional Neural Network (CNN) and Bidirectional-Long Short Term Memory (BiLSTM) network to encode entities and learn dependencies among them, respectively. We evaluate our model on a large and recent dataset and compare results with previous neural methods. Experimental results show that our model consistently outperforms the previous model for the task of relation extraction on tabular data. We perform comprehensive error analyses and ablation study to show the contribution of various components of our model. Finally, we discuss the usefulness and trade-offs of our approach, and provide suggestions for fostering further research.