Summary of Argument-aware Approach to Event Linking, by I-hung Hsu et al.
Argument-Aware Approach To Event Linking
by I-Hung Hsu, Zihan Xue, Nilay Pochh, Sahil Bansal, Premkumar Natarajan, Jayanth Srinivasa, Nanyun Peng
First submitted to arxiv on: 22 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 paper presents an argument-aware approach to improve event linking models by recognizing key information about event mentions and handling “out-of-KB” scenarios. The authors augment input text with tagged event argument information to enhance recognition of event mentions, and synthesize out-of-KB training examples from in-KB instances through controlled manipulation of event arguments. The experiment shows significant enhancements in both in-KB and out-of-KB scenarios, with a notable 22% improvement in out-of-KB evaluations. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Event linking is a way to connect mentions of events in text with relevant information in a knowledge base (KB). This paper helps improve event linking by looking at the arguments or details surrounding each event. It also solves a problem where events are not mentioned in the KB, which happens often because there isn’t enough information about these types of events. The authors try two new ideas: adding more information to the text before trying to link it with the KB, and creating fake examples that aren’t in the KB so the model can practice recognizing those too. This helps the model get better at both connecting events with the KB and handling situations where the event isn’t in the KB. |
Keywords
» Artificial intelligence » Knowledge base
