Attentive Tree-structured Network for Monotonicity Reasoning
Abstract
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.
Keywords
Cite
@article{arxiv.2101.00540,
title = {Attentive Tree-structured Network for Monotonicity Reasoning},
author = {Zeming Chen},
journal= {arXiv preprint arXiv:2101.00540},
year = {2021}
}
Comments
Proceeding of the First Workshop on Natural Logic Meets Machine Learning, Association for Computational Linguistics