Supporting Context Monotonicity Abstractions in Neural NLI Models

05/17/2021
by   Julia Rozanova, et al.
3

Natural language contexts display logical regularities with respect to substitutions of related concepts: these are captured in a functional order-theoretic property called monotonicity. For a certain class of NLI problems where the resulting entailment label depends only on the context monotonicity and the relation between the substituted concepts, we build on previous techniques that aim to improve the performance of NLI models for these problems, as consistent performance across both upward and downward monotone contexts still seems difficult to attain even for state-of-the-art models. To this end, we reframe the problem of context monotonicity classification to make it compatible with transformer-based pre-trained NLI models and add this task to the training pipeline. Furthermore, we introduce a sound and complete simplified monotonicity logic formalism which describes our treatment of contexts as abstract units. Using the notions in our formalism, we adapt targeted challenge sets to investigate whether an intermediate context monotonicity classification task can aid NLI models' performance on examples exhibiting monotonicity reasoning.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/30/2020

TaxiNLI: Taking a Ride up the NLU Hill

Pre-trained Transformer-based neural architectures have consistently ach...
research
07/06/2023

NatLogAttack: A Framework for Attacking Natural Language Inference Models with Natural Logic

Reasoning has been a central topic in artificial intelligence from the b...
research
08/04/2019

Separating Argument Structure from Logical Structure in AMR

The AMR (Abstract Meaning Representation) formalism for representing mea...
research
05/20/2015

Multi-Context Systems for Reactive Reasoning in Dynamic Environments

We show in this paper how managed multi-context systems (mMCSs) can be t...
research
09/16/2019

Probing Natural Language Inference Models through Semantic Fragments

Do state-of-the-art models for language understanding already have, or c...
research
05/15/2023

Estimating the Causal Effects of Natural Logic Features in Neural NLI Models

Rigorous evaluation of the causal effects of semantic features on langua...
research
12/15/2021

Decomposing Natural Logic Inferences in Neural NLI

In the interest of interpreting neural NLI models and their reasoning st...

Please sign up or login with your details

Forgot password? Click here to reset