Hyperbolic Relevance Matching for Neural Keyphrase Extraction

TL;DR

This paper introduces HyperMatch, a hyperbolic space-based model for keyphrase extraction that effectively captures hierarchical structures and improves relevance estimation, outperforming existing methods on multiple benchmarks.

Contribution

The paper proposes a novel hyperbolic matching model that embeds phrases and documents in the same hyperbolic space for improved relevance estimation in keyphrase extraction.

Findings

HyperMatch outperforms state-of-the-art baselines on six benchmark datasets.

Embedding in hyperbolic space enhances hierarchical structure modeling.

The model effectively estimates phrase-document relevance via hyperbolic distance.

Abstract

Keyphrase extraction is a fundamental task in natural language processing and information retrieval that aims to extract a set of phrases with important information from a source document. Identifying important keyphrase is the central component of the keyphrase extraction task, and its main challenge is how to represent information comprehensively and discriminate importance accurately. In this paper, to address these issues, we design a new hyperbolic matching model (HyperMatch) to represent phrases and documents in the same hyperbolic space and explicitly estimate the phrase-document relevance via the Poincar\'e distance as the important score of each phrase. Specifically, to capture the hierarchical syntactic and semantic structure information, HyperMatch takes advantage of the hidden representations in multiple layers of RoBERTa and integrates them as the word embeddings via an adaptive mixing layer. Meanwhile, considering the hierarchical structure hidden in the document, HyperMatch embeds both phrases and documents in the same hyperbolic space via a hyperbolic phrase encoder and a hyperbolic document encoder. This strategy can further enhance the estimation of phrase-document relevance due to the good properties of hyperbolic space. In this setting, the keyphrase extraction can be taken as a matching problem and effectively implemented by minimizing a hyperbolic margin-based triplet loss. Extensive experiments are conducted on six benchmarks and demonstrate that HyperMatch outperforms the state-of-the-art baselines.