Summary of Semantic Role Labeling Of Nombank Partitives, by Adam Meyers et al.
Semantic Role Labeling of NomBank Partitives
by Adam Meyers, Advait Pravin Savant, John E. Ortega
First submitted to arxiv on: 18 Dec 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 This paper investigates Semantic Role Labeling (SRL) for English partitive nouns, focusing on NomBank annotated corpus. The authors present various systems utilizing traditional machine learning, transformer-based approaches, and ensembling methods. Notably, their highest-scoring system achieves F1 scores of 91.74% using Penn Treebank parses and 91.12% with Berkeley Neural parser. This research explores both classroom and experimental settings for developing SRL systems. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about understanding the meanings of phrases that contain partitive nouns, like “5 percent of the price”. The authors compare different ways to approach this task using machine learning techniques. They find that their best method achieves a high accuracy rate (around 91%) when using certain parsers. This research was done in both classroom and laboratory settings. |
Keywords
» Artificial intelligence » Machine learning » Transformer
