Summary of Fcds: Fusing Constituency and Dependency Syntax Into Document-level Relation Extraction, by Xudong Zhu et al.
FCDS: Fusing Constituency and Dependency Syntax into Document-Level Relation Extraction
by Xudong Zhu, Zhao Kang, Bei Hui
First submitted to arxiv on: 4 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 This paper proposes a new approach to Document-level Relation Extraction (DocRE), which identifies relation labels between entities within a single document. Current state-of-the-art methods use graph structures to capture dependency syntax information, but this is insufficient to fully exploit the rich syntax information in documents. The proposed method fuses constituency and dependency syntax into DocRE, using constituency syntax to aggregate sentence-level information and select instructive sentences for entity pairs. It also enhances the graph structure with dependency syntax information and chooses paths between entity pairs based on the dependency graph. Experimental results on datasets from various domains demonstrate the effectiveness of the proposed method. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a new way to understand relationships between things in documents, like articles or books. Current methods are good at understanding how words relate to each other, but they’re not as good at understanding the bigger picture. The new approach combines two types of information: what’s happening within sentences and how those sentences relate to each other. This helps computers better identify relationships between important things in documents. |
Keywords
» Artificial intelligence » Syntax
