Conference Proceeding Article
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.
Natural language processing, Deep learning
Artificial Intelligence and Robotics | Databases and Information Systems
Data Science and Engineering
ICLR 2017: International Conference on Learning Representations, Toulon, France, April 24-26: Proceedings
City or Country
WANG, Shuohang and Jing JIANG.
A compare-aggregate model for matching text sequences. (2017). ICLR 2017: International Conference on Learning Representations, Toulon, France, April 24-26: Proceedings. 1-15. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/3653
Copyright Owner and License
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.