Predicting Performance for Natural Language Processing Tasks

TL;DR

This paper introduces regression models that predict NLP experiment outcomes based on settings, enabling plausible performance estimation without exhaustive testing across tasks, languages, and domains.

Contribution

It presents a novel approach to predict NLP model performance using regression, reducing the need for extensive experiments across diverse settings.

Findings

Predictors outperform baselines and human experts in accuracy.

Models generalize well to unseen languages and architectures.

Method helps identify representative experiments for broader predictions.

Abstract

Given the complexity of combinations of tasks, languages, and domains in natural language processing (NLP) research, it is computationally prohibitive to exhaustively test newly proposed models on each possible experimental setting. In this work, we attempt to explore the possibility of gaining plausible judgments of how well an NLP model can perform under an experimental setting, without actually training or testing the model. To do so, we build regression models to predict the evaluation score of an NLP experiment given the experimental settings as input. Experimenting on 9 different NLP tasks, we find that our predictors can produce meaningful predictions over unseen languages and different modeling architectures, outperforming reasonable baselines as well as human experts. Going further, we outline how our predictor can be used to find a small subset of representative experiments that should be run in order to obtain plausible predictions for all other experimental settings.