J2N -- Nominal Adjective Identification and its Application

TL;DR

This paper introduces a new approach to handle nominal adjectives in NLP by treating them as a separate POS tag, improving syntactic analysis and structural understanding across various NLP tasks.

Contribution

It proposes a novel POS tagging scheme for nominal adjectives and evaluates its effectiveness using multiple models, including HMMs, MaxEnt, Spacy, and fine-tuned BERT.

Findings

Reclassifying NAs as 'JN' improves POS tagging accuracy.

The approach benefits BIO chunking and coreference resolution.

Experimental results demonstrate the feasibility of the method.

Abstract

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.