J2N -- Nominal Adjective Identification and its Application

Lemeng Qi, Yang Han, Zhuotong Xie
9/22/2024
cs.CL

No official code found. Best implementation: DeadCardassian/POSCorefImpact (2 stars, last commit 2024-10-01).

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.

View on arXivView PDF

Code Implementations(1)

DeadCardassian/POSCorefImpactCommunity100%
20PythonSep 5, 20242 years ago

Similar Papers

POS-tagging to highlight the skeletal structure of sentences

78% match1 repo2024

Inferring Adjective Hypernyms with Language Models to Increase the Connectivity of Open English Wordnet

78% match2025

Exploring the Performance of Large Language Models on Subjective Span Identification Tasks

78% match1 repo2026

Topic Aware Probing: From Sentence Length Prediction to Idiom Identification how reliant are Neural Language Models on Topic?

76% match2024

Author-Specific Linguistic Patterns Unveiled: A Deep Learning Study on Word Class Distributions

76% match2025

Persian Pronoun Resolution: Leveraging Neural Networks and Language Models

75% match2024

Cite this paper

@article{qi2024nominal,
  title  = {J2N -- Nominal Adjective Identification and its Application},
  author = {Lemeng Qi and Yang Han and Zhuotong Xie},
  year   = {2024},
  eprint = {2409.14374},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2409.14374v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2409.14374.svg)](https://codeofpaper.com/paper/2409.14374)

Discussion