DeepAI AI Chat
Log In Sign Up

MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity

10/19/2019
by   Hai Hu, et al.
0

We present a new logic-based inference engine for natural language inference (NLI) called MonaLog, which is based on natural logic and the monotonicity calculus. In contrast to existing logic-based approaches, our system is intentionally designed to be as lightweight as possible, and operates using a small set of well-known (surface-level) monotonicity facts about quantifiers, lexical items and tokenlevel polarity information. Despite its simplicity, we find our approach to be competitive with other logic-based NLI models on the SICK benchmark. We also use MonaLog in combination with the current state-of-the-art model BERT in a variety of settings, including for compositional data augmentation. We show that MonaLog is capable of generating large amounts of high-quality training data for BERT, improving its accuracy on SICK.

READ FULL TEXT

page 1

page 2

page 3

page 4

03/28/2019

Distilling Task-Specific Knowledge from BERT into Simple Neural Networks

In the natural language processing literature, neural networks are becom...
02/28/2022

The impact of lexical and grammatical processing on generating code from natural language

Considering the seq2seq architecture of TranX for natural language to co...
10/29/2020

Learning as Abduction: Trainable Natural Logic Theorem Prover for Natural Language Inference

Tackling Natural Language Inference with a logic-based method is becomin...
05/20/2018

Generating High-Quality Surface Realizations Using Data Augmentation and Factored Sequence Models

This work presents a new state of the art in reconstruction of surface r...
10/07/2021

A Logic-Based Framework for Natural Language Inference in Dutch

We present a framework for deriving inference relations between Dutch se...
10/04/2020

Reverse Operation based Data Augmentation for Solving Math Word Problems

Automatically solving math word problems is a critical task in the field...