Summary of Linear Cross-document Event Coreference Resolution with X-amr, by Shafiuddin Rehan Ahmed et al.
Linear Cross-document Event Coreference Resolution with X-AMR
by Shafiuddin Rehan Ahmed, George Arthur Baker, Evi Judge, Michael Regan, Kristin Wright-Bettner, Martha Palmer, James H. Martin
First submitted to arxiv on: 25 Mar 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 proposed X-AMR graphical representation of events anchors mentions using a cross-document version of Abstract Meaning Representation. This simplifies Event Coreference Resolution (ECR), making it cost-effective, compositional, and interpretable for Large Language Models (LLMs). A novel multi-hop coreference algorithm is applied to the event graphs, reducing ECR’s quadratic difficulty. To evaluate this approach, an existing ECR benchmark dataset is enriched with event graphs using an annotator-friendly tool. GPT-4, the newest LLM by OpenAI, is employed for annotations and compared against human performance. The research aims to advance the state-of-the-art for efficient ECR and shed light on potential shortcomings of current LLMs at this task. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Event Coreference Resolution (ECR) is a challenging task that can be costly both for automated systems and manual annotations. Researchers have proposed a new approach to simplify ECR by representing events as graphs, which makes it more efficient and interpretable. This method uses a cross-document version of Abstract Meaning Representation and applies a novel multi-hop coreference algorithm. The researchers also enriched an existing ECR benchmark dataset with event graphs and used GPT-4, the newest LLM by OpenAI, for annotations. |
Keywords
» Artificial intelligence » Coreference » Gpt
