J2N -- Nominal Adjective Identification and its Application
This addresses a specific linguistic problem in NLP for researchers and practitioners, but it is incremental as it builds on existing methods for a niche issue.
The paper tackles the challenge of nominal adjectives in NLP by proposing a distinct POS tag 'JN', showing it improves syntactic analysis accuracy in tasks like POS tagging, BIO chunking, and coreference resolution, with experimental results using HMMs, MaxEnt, Spacy, and a fine-tuned BERT model.
This paper explores the challenges posed by nominal adjectives (NAs) in natural language processing (NLP) tasks, particularly in part-of-speech (POS) tagging. We propose treating NAs as a distinct POS tag, "JN," and investigate its impact on POS tagging, BIO chunking, and coreference resolution. Our study shows that reclassifying NAs can improve the accuracy of syntactic analysis and structural understanding in NLP. We present experimental results using Hidden Markov Models (HMMs), Maximum Entropy (MaxEnt) models, and Spacy, demonstrating the feasibility and potential benefits of this approach. Additionally we finetuned a bert model to identify the NA in untagged text.