Embarrassingly Simple Performance Prediction for Abductive Natural Language Inference

TL;DR

This paper introduces a simple, fast method to predict the performance of models on abductive natural language inference tasks by using cosine similarity of sentence embeddings, saving significant time in model selection.

Contribution

It proposes a novel performance prediction approach based on embedding similarity that correlates well with actual model accuracy, eliminating the need for extensive fine-tuning.

Findings

Cosine similarity correlates with classifier accuracy (Pearson r=0.65).

Performance prediction is significantly faster (less than a minute).

Method enables efficient model selection for abductive NLI.

Abstract

The task of abductive natural language inference (\alpha{}nli), to decide which hypothesis is the more likely explanation for a set of observations, is a particularly difficult type of NLI. Instead of just determining a causal relationship, it requires common sense to also evaluate how reasonable an explanation is. All recent competitive systems build on top of contextualized representations and make use of transformer architectures for learning an NLI model. When somebody is faced with a particular NLI task, they need to select the best model that is available. This is a time-consuming and resource-intense endeavour. To solve this practical problem, we propose a simple method for predicting the performance without actually fine-tuning the model. We do this by testing how well the pre-trained models perform on the \alpha{}nli task when just comparing sentence embeddings with cosine similarity to what the performance that is achieved when training a classifier on top of these embeddings. We show that the accuracy of the cosine similarity approach correlates strongly with the accuracy of the classification approach with a Pearson correlation coefficient of 0.65. Since the similarity computation is orders of magnitude faster to compute on a given dataset (less than a minute vs. hours), our method can lead to significant time savings in the process of model selection.