Dealing with Metonymic Readings of Named Entities
Thierry Poibeau
Abstract
The aim of this paper is to propose a method for tagging named entities (NE), using natural language processing techniques. Beyond their literal meaning, named entities are frequently subject to metonymy. We show the limits of current NE type hierarchies and detail a new proposal aiming at dynamically capturing the semantics of entities in context. This model can analyze complex linguistic phenomena like metonymy, which are known to be difficult for natural language processing but crucial for most applications. We present an implementation and some test using the French ESTER corpus and give significant results.
Create a lesson
Related papers
Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation
Zixing Lei, Gengze Zhou, Xiong-Hui Chen et al.
Augmenting Human Performance with an XR Agent Learning from Online Behavior and BCI Evidence
Ziheng Li, Xichen He, Haoyan Chen et al.
Will the User Ever Know? Covert Indirect Prompt Injection on Tool-Using LLM Agents
Yunseok Lee, Yunji Kim, Woojin Lee
Co-Annotator: Expert-Distilled ViT and VLM for Visual and Documentation Guidance in Age-Related Macular Degeneration
Ziheng "Leo" Li, Benjamin Freeman, Akshay Raman et al.
Answer Probing-Guided Search for Diverse Solution Exploration of LLMs
Yi Fang, Que Shen, Chengpeng Li et al.
Ignorance or Incompetence? Constructing Knowledge-Gated, Verifiable Tasks for LLM Agents
Hanlin Tian, Minhao Li, Yu Mi et al.