Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic

09/18/2021
by   Zijun Wu, et al.
0

Natural language inference (NLI) aims to determine the logical relationship between two sentences among the target labels Entailment, Contradiction, and Neutral. In recent years, deep learning models have become a prevailing approach to NLI, but they lack interpretability and explainability. In this work, we address the explainability for NLI by weakly supervised logical reasoning, and propose an Explainable Phrasal Reasoning (EPR) approach. Our model first detects phrases as the semantic unit and aligns corresponding phrases. Then, the model predicts the NLI label for the aligned phrases, and induces the sentence label by fuzzy logic formulas. Our EPR is almost everywhere differentiable and thus the system can be trained end-to-end in a weakly supervised manner. We annotated a corpus and developed a set of metrics to evaluate phrasal reasoning. Results show that our EPR yields much more meaningful explanations in terms of F scores than previous studies. To the best of our knowledge, we are the first to develop a weakly supervised phrasal reasoning model for the NLI task.

READ FULL TEXT
research
02/14/2020

Analyzing Differentiable Fuzzy Logic Operators

In recent years there has been a push to integrate symbolic AI and deep ...
research
11/26/2022

Who are you referring to? Weakly supervised coreference resolution with multimodal grounding

Coreference resolution aims at identifying words and phrases which refer...
research
05/03/2017

Weakly-supervised Visual Grounding of Phrases with Linguistic Structures

We propose a weakly-supervised approach that takes image-sentence pairs ...
research
02/03/2023

From slides (through tiles) to pixels: an explainability framework for weakly supervised models in pre-clinical pathology

In pre-clinical pathology, there is a paradox between the abundance of r...
research
05/19/2022

LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsing

Semantic parsing is the task of producing structured meaning representat...
research
12/25/2020

LOREN: Logic Enhanced Neural Reasoning for Fact Verification

Given a natural language statement, how to verify whether it is supporte...
research
07/13/2021

Enforcing Consistency in Weakly Supervised Semantic Parsing

The predominant challenge in weakly supervised semantic parsing is that ...

Please sign up or login with your details

Forgot password? Click here to reset