Attentive Tree-structured Network for Monotonicity Reasoning
This paper tackles the problem of improving monotonicity reasoning, specifically downward inference, for researchers working on natural language inference.
The paper addresses the poor performance of state-of-the-art neural models in downward inference for monotonicity reasoning. The authors developed an attentive tree-structured neural network that outperforms existing models on the Monotonicity Entailment Dataset (MED).
Many state-of-art neural models designed for monotonicity reasoning perform poorly on downward inference. To address this shortcoming, we developed an attentive tree-structured neural network. It consists of a tree-based long-short-term-memory network (Tree-LSTM) with soft attention. It is designed to model the syntactic parse tree information from the sentence pair of a reasoning task. A self-attentive aggregator is used for aligning the representations of the premise and the hypothesis. We present our model and evaluate it using the Monotonicity Entailment Dataset (MED). We show and attempt to explain that our model outperforms existing models on MED.