Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends

TL;DR

Maverick is a simple, resource-efficient coreference resolution system that outperforms large autoregressive models, achieving state-of-the-art results with significantly less memory and faster inference.

Contribution

The paper introduces Maverick, a lightweight pipeline that challenges recent trends by providing a more efficient yet highly effective coreference resolution method.

Findings

Outperforms models with up to 13 billion parameters

Uses only 0.006x the memory resources of previous systems

Achieves 170x faster inference than prior state-of-the-art models

Abstract

Large autoregressive generative models have emerged as the cornerstone for achieving the highest performance across several Natural Language Processing tasks. However, the urge to attain superior results has, at times, led to the premature replacement of carefully designed task-specific approaches without exhaustive experimentation. The Coreference Resolution task is no exception; all recent state-of-the-art solutions adopt large generative autoregressive models that outperform encoder-based discriminative systems. In this work,we challenge this recent trend by introducing Maverick, a carefully designed - yet simple - pipeline, which enables running a state-of-the-art Coreference Resolution system within the constraints of an academic budget, outperforming models with up to 13 billion parameters with as few as 500 million parameters. Maverick achieves state-of-the-art performance on the CoNLL-2012 benchmark, training with up to 0.006x the memory resources and obtaining a 170x faster inference compared to previous state-of-the-art systems. We extensively validate the robustness of the Maverick framework with an array of diverse experiments, reporting improvements over prior systems in data-scarce, long-document, and out-of-domain settings. We release our code and models for research purposes at https://github.com/SapienzaNLP/maverick-coref.