CoRec: An Easy Approach for Coordination Recognition
It addresses the problem of slow and error-prone syntactic parsers in coordination recognition for NLP applications, offering an incremental improvement.
The paper tackles the coordination recognition task by proposing CoRec, a pipeline model that identifies coordinators and detects conjunct boundaries, achieving improved efficiency and effectiveness across various domains and positively impacting downstream Open IE models.
In this paper, we observe and address the challenges of the coordination recognition task. Most existing methods rely on syntactic parsers to identify the coordinators in a sentence and detect the coordination boundaries. However, state-of-the-art syntactic parsers are slow and suffer from errors, especially for long and complicated sentences. To better solve the problems, we propose a pipeline model COordination RECognizer (CoRec). It consists of two components: coordinator identifier and conjunct boundary detector. The experimental results on datasets from various domains demonstrate the effectiveness and efficiency of the proposed method. Further experiments show that CoRec positively impacts downstream tasks, improving the yield of state-of-the-art Open IE models.