A Compare-Aggregate Model for Matching Text Sequences
This addresses sequence matching for NLP tasks like machine comprehension, but it is incremental as it focuses on optimizing comparison functions within an existing framework.
The paper tackles the problem of comparing text sequences for NLP tasks by proposing a compare-aggregate framework using word-level matching and CNNs, finding that simple element-wise comparison functions outperform standard neural networks and neural tensor networks on four datasets.
Many NLP tasks including machine comprehension, answer selection and text entailment require the comparison between sequences. Matching the important units between sequences is a key to solve these problems. In this paper, we present a general "compare-aggregate" framework that performs word-level matching followed by aggregation using Convolutional Neural Networks. We particularly focus on the different comparison functions we can use to match two vectors. We use four different datasets to evaluate the model. We find that some simple comparison functions based on element-wise operations can work better than standard neural network and neural tensor network.