Results of the WNUT2017 Shared Task on Novel and Emerging Entity Recognition

TLDR

Named entity recognition is crucial for downstream tasks but suffers recall problems in noisy text due to novel entities and surface forms, as illustrated by hard‑to‑detect examples such as “kktny.” The shared task aims to identify unusual, previously‑unseen entities in emerging discussions. The task defines emerging and rare entities, supplies datasets, and evaluates participants’ ability to detect and classify them. The evaluation measured how well entries detected and classified novel and emerging named entities in noisy text.

Abstract

This shared task focuses on identifying unusual, previously-unseen entities in the context of emerging discussions. Named entities form the basis of many modern approaches to other tasks (like event clustering and summarization), but recall on them is a real problem in noisy text - even among annotators. This drop tends to be due to novel entities and surface forms. Take for example the tweet “so.. kktny in 30 mins?!” – even human experts find the entity ‘kktny’ hard to detect and resolve. The goal of this task is to provide a definition of emerging and of rare entities, and based on that, also datasets for detecting these entities. The task as described in this paper evaluated the ability of participating entries to detect and classify novel and emerging named entities in noisy text.