Robust Natural Language Representation Learning for Natural Language Inference by Projecting Superficial Words out

25 Sep 2019  ·  Wanyun Cui, Guangyu Zheng, Wei Wang ·

In natural language inference, the semantics of some words do not affect the inference. Such information is considered superficial and brings overfitting. How can we represent and discard such superficial information? In this paper, we use first order logic (FOL) - a classic technique from meaning representation language – to explain what information is superficial for a given sentence pair. Such explanation also suggests two inductive biases according to its properties. We proposed a neural network-based approach that utilizes the two inductive biases. We obtain substantial improvements over extensive experiments.

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here