Summary of Small Models Are (still) Effective Cross-domain Argument Extractors, by William Gantt and Aaron Steven White
Small Models Are (Still) Effective Cross-Domain Argument Extractors
by William Gantt, Aaron Steven White
First submitted to arxiv on: 12 Apr 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
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 This study investigates two promising methods – question answering (QA) and template infilling (TI) – for effective ontology transfer in event argument extraction (EAE). The researchers explore zero-shot transfer using both techniques on six major EAE datasets at the sentence and document levels. Notably, they challenge the reliance on large language models (LLMs) by showing that smaller models trained on a suitable source ontology can achieve superior performance to GPT-3.5 or GPT-4 in zero-shot extraction. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at two ways to help computers understand events and their relationships: question answering (QA) and template infilling (TI). It tests how well these methods work when transferring knowledge from one event dataset to another, without any extra training. The results show that smaller models trained on a good starting point can be better than using super powerful language models like GPT-3.5 or GPT-4. |
Keywords
» Artificial intelligence » Gpt » Question answering » Zero shot
