Nominal Compound Chain Extraction: A New Task for Semantic-enriched Lexical Chain
This addresses the limitation of shallow lexical chains in NLP by enabling semantic-aware compound extraction, though it is incremental as it builds on existing methods like BERT.
The paper introduces Nominal Compound Chain Extraction (NCCE), a new task for extracting and clustering nominal compounds with shared semantic topics, and proposes a joint two-stage model using BERT and HowNet, with experiments on a manually annotated corpus showing its effectiveness.
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.