Nominal Compound Chain Extraction: A New Task for Semantic-enriched Lexical Chain

TL;DR

This paper introduces Nominal Compound Chain Extraction (NCCE), a new NLP task that identifies and clusters nominal compounds sharing semantic topics, enhancing the understanding of text structure beyond shallow lexical analysis.

Contribution

It proposes a novel two-stage joint framework using BERT and HowNet for semantic-aware extraction and clustering of nominal compounds, addressing limitations of previous lexical chain methods.

Findings

NCCE is necessary for better semantic text analysis.

The joint framework outperforms baseline methods.

Experimental results validate the effectiveness of the approach.

Abstract

Lexical chain consists of cohesion words in a document, which implies the underlying structure of a text, and thus facilitates downstream NLP tasks. Nevertheless, existing work focuses on detecting the simple surface lexicons with shallow syntax associations, ignoring the semantic-aware lexical compounds as well as the latent semantic frames, (e.g., topic), which can be much more crucial for real-world NLP applications. In this paper, we introduce a novel task, Nominal Compound Chain Extraction (NCCE), extracting and clustering all the nominal compounds that share identical semantic topics. In addition, we model the task as a two-stage prediction (i.e., compound extraction and chain detection), which is handled via a proposed joint framework. The model employs the BERT encoder to yield contextualized document representation. Also, HowNet is exploited as external resources for offering rich sememe information. The experiments are based on our manually annotated corpus, and the results prove the necessity of the NCCE task as well as the effectiveness of our joint approach.