A Compare-Aggregate Model for Matching Text SequencesDownload PDF

27 Sep 2020 (modified: 03 Mar 2017)ICLR 2017 conference submissionReaders: Everyone
  • TL;DR: A general "compare-aggregate" framework that performs word-level matching followed by aggregation using Convolutional Neural Networks
  • Abstract: 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.
  • Keywords: Natural language processing, Deep learning
  • Conflicts: smu.edu.sg
14 Replies

Loading