Summary of Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends, by Giuliano Martinelli et al.
Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends
by Giuliano Martinelli, Edoardo Barba, Roberto Navigli
First submitted to arxiv on: 31 Jul 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper challenges the recent trend of using large generative autoregressive models for coreference resolution, instead proposing a carefully designed pipeline called Maverick that achieves state-of-the-art performance with significantly fewer parameters and resources. The Maverick framework is validated through various experiments, including data-scarce, long-document, and out-of-domain settings, demonstrating improvements over prior systems. The authors release their code and models for research purposes. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper shows how to make a coreference resolution system that uses less computer power and memory than other top systems, but still performs as well or better. This is important because it can help researchers who don’t have access to lots of resources. The new system, called Maverick, does this by using a special pipeline that is designed carefully. It’s tested on different kinds of data and shows improvements over previous systems. |
Keywords
* Artificial intelligence * Autoregressive * Coreference
