Comparing Convolutional Neural Networks to Traditional Models for Slot Filling
This work addresses slot filling for natural language processing applications, but it is incremental as it builds on existing relation classification methods.
The paper tackled relation classification for slot filling by proposing a convolutional neural network that splits input sentences into three parts based on relation arguments, and showed that combining different methods outperforms individual approaches, with performance analysis across genres.
We address relation classification in the context of slot filling, the task of finding and evaluating fillers like "Steve Jobs" for the slot X in "X founded Apple". We propose a convolutional neural network which splits the input sentence into three parts according to the relation arguments and compare it to state-of-the-art and traditional approaches of relation classification. Finally, we combine different methods and show that the combination is better than individual approaches. We also analyze the effect of genre differences on performance.